Compare commits

...

304 Commits

Author SHA1 Message Date
0e703d92ac Merge branch 'release/0.9.26' 2015-05-28 18:21:14 +02:00
12b90600eb core: moved guards 2015-05-28 18:18:23 +02:00
2587b0ea62 Merge branch 'release/0.9.26' into develop 2015-05-28 18:01:54 +02:00
f082c1b895 Merge branch 'release/0.9.26' 2015-05-28 18:01:40 +02:00
d51d74eb55 cmd/geth: bump version v0.9.26 2015-05-28 17:43:05 +02:00
35806ccc1c build server fix 2015-05-28 17:18:13 +02:00
b25e8b7079 Merge pull request #1142 from obscuren/100-pct-block-prop
eth: 100% block propogation
2015-05-28 08:07:11 -07:00
e5d7627427 eth: 100% block propogation 2015-05-28 17:01:44 +02:00
a225ef9c13 Merge pull request #1140 from Gustav-Simonsson/fix_account_unlock_logging
Validate account length and avoid slicing in logging
2015-05-28 07:39:13 -07:00
b6e137b2b4 Merge pull request #1141 from obscuren/parallelisation-issue
Parallelisation issue
2015-05-28 07:37:37 -07:00
03178a77b6 Merge pull request #1132 from obscuren/log_optimisations
core: log optimisations
2015-05-28 07:35:07 -07:00
16038b4e67 core: added bad block 2015-05-28 16:26:19 +02:00
109f995684 core: log block hash during nonce error 2015-05-28 15:46:36 +02:00
75f5ae80fd core: partially removed nonce parallelisation and added merge error chk
Invalid forks are now detected

Current setup of parellelisation actually inserts bad blocks. This fix
is tmp until a better one is found
2015-05-28 15:35:50 +02:00
9138955ba5 Validate account length and avoid slicing in logging 2015-05-28 15:20:05 +02:00
4baa5ca963 Merge pull request #1137 from obscuren/web3_update
cmd/geth: updated web3
2015-05-28 04:40:14 -07:00
598e454d46 cmd/geth: updated web3 2015-05-28 13:24:09 +02:00
9f467c387a Merge pull request #1123 from fjl/lean-blockchain-commands
cmd/geth: leaner blockchain commands
2015-05-28 04:17:47 -07:00
8add3bb009 Merge pull request #1135 from karalabe/tempban-invalid-hashes
core, eth/downloader: expose the bad hashes, check in downloader
2015-05-28 04:13:08 -07:00
29b0480cfb core, eth/downloader: expose the bad hashes, check in downloader 2015-05-28 14:03:10 +03:00
e84bbcce3c cmd/geth: don't flush databases after import 2015-05-28 01:20:58 +02:00
e1fe75e3b6 cmd/utils: use constant for import batch size 2015-05-28 01:20:58 +02:00
a8bc2181c9 cmd/utils: skip batches with known blocks during import
This makes block importing restartable.
2015-05-28 01:20:58 +02:00
67effb94b6 cmd/geth, cmd/utils: make chain importing interruptible
Interrupting import with Ctrl-C could cause database corruption
because the signal wasn't handled. utils.ImportChain now checks
for a queued interrupt on every batch.
2015-05-28 01:09:26 +02:00
705beb4c25 cmd/utils: print errors only once if stdout and stderr are the same file 2015-05-28 01:09:26 +02:00
74706a0f02 cmd/geth, cmd/utils: rename utils.Get* -> utils.Make*
The renaming should make it clearer that these functions create a new
instance for every call. @obscuren suggested this renaming a while ago.
2015-05-28 01:09:26 +02:00
8e4512a5e7 p2p/nat: bump timeout in TestAutoDiscRace 2015-05-28 01:09:26 +02:00
651030c98d cmd/geth: move blockchain commands to chaincmd.go 2015-05-28 01:09:26 +02:00
62671c93c4 cmd/mist: use utils.SetupLogger 2015-05-28 01:09:26 +02:00
3b9808f23c cmd/geth, cmd/utils: don't use Ethereum for import, export and upgradedb
The blockchain commands don't need the full stack. With this change,
p2p, miner, downloader, etc are no longer started for blockchain
operations.
2015-05-28 01:09:26 +02:00
e3253b5d5e core: fixed an issue with storing receipts 2015-05-28 01:00:23 +02:00
27e0d2a973 Merge pull request #1128 from karalabe/hard-disconnect-trial
eth: hard disconnect if a peer is flaky
2015-05-27 15:28:39 -07:00
5479be9f64 Merge pull request #1129 from obscuren/database_cache_removal
ethdb, common: cache removal
2015-05-27 10:00:08 -07:00
903b95fffa Merge pull request #1124 from karalabe/detaied-download-progress
cmd/geth: expand admin.progress() to something meaningful
2015-05-27 09:05:46 -07:00
020006a8ed common, ethdb: removed caching and LastTD 2015-05-27 18:03:16 +02:00
5235e01b8d eth: hard disconnect if a peer is flaky 2015-05-27 18:58:51 +03:00
7595716816 core: adjust gas calculation 2015-05-27 17:01:28 +02:00
3f91ee4ff8 cmd/geth: expand admin.progress() to something meaningful 2015-05-27 16:46:46 +03:00
8951a03db3 Merge pull request #1121 from obscuren/miner_time_fix
Miner time fix
2015-05-27 04:51:42 -07:00
e13f413ef5 Merge pull request #1112 from fjl/fix-console-exit
cmd/geth: exit the console cleanly when interrupted
2015-05-27 04:40:29 -07:00
69f7a1da5a Merge pull request #1122 from Gustav-Simonsson/improve_validate_header_comments
Update ValidateHeader comments
2015-05-27 04:34:34 -07:00
912ae80350 miner: Added 5 blocks wait in prep for #1067 2015-05-27 13:33:52 +02:00
12650e16d3 core, miner: fixed miner time issue and removed future blocks
* Miner should no longer generate blocks with a time stamp less or equal
than it's parent.
* Future blocks are no longer processed and queued directly.
  Closes #1118
2015-05-27 13:30:52 +02:00
34729c365b Merge pull request #1067 from carver/deep-mining-log
miner: log locally mined blocks after they are 5-deep in the chain
2015-05-27 04:30:31 -07:00
bf5f0b1d0c Update ValidateHeader comments 2015-05-27 13:30:24 +02:00
4b29e5ba85 Merge pull request #1120 from Gustav-Simonsson/revert_gas_limit_change
Revert "core: block.gasLimit - parent.gasLimit <= parent.gasLimit / G…
2015-05-27 04:23:55 -07:00
14955bd454 Revert "core: block.gasLimit - parent.gasLimit <= parent.gasLimit / GasLimitBoundDivisor"
This reverts commit be2b0501b5.
2015-05-27 13:01:06 +02:00
de12183d38 deep-mining-log: need ring buffer to be one bigger for all-blocks-mined case 2015-05-26 18:55:52 -07:00
6019f1bb0a deep-mining-log: only track non-stale blocks
if you track stale blocks, then you quickly overflow your ring buffer in the local network case where you're mining every block and generating a lot of stales.
2015-05-26 18:54:56 -07:00
f5ce848cfe Merge branch 'release/0.9.25' into develop 2015-05-27 02:07:13 +02:00
70867904a0 Merge branch 'release/0.9.25' 2015-05-27 02:07:03 +02:00
2c532a7255 cmd/geth: bump version 0.9.25 2015-05-27 02:06:52 +02:00
aada35af9b Merge pull request #1114 from obscuren/develop
core: block.gasLimit - parent.gasLimit <= parent.gasLimit / GasLimitB…
2015-05-26 17:04:42 -07:00
be2b0501b5 core: block.gasLimit - parent.gasLimit <= parent.gasLimit / GasLimitBoundDivisor 2015-05-27 01:52:03 +02:00
3590591e67 Merge pull request #1113 from obscuren/develop
core: block database version update
2015-05-26 16:47:10 -07:00
222249e622 cmd/geth: Flush instead of close. This solves a nil ptr error 2015-05-27 01:38:41 +02:00
b2f2806055 cmd/geth, core: Updated DB version & seedhash debug method 2015-05-27 01:38:41 +02:00
9253fc337e cmd/geth: exit the console cleanly when interrupted
This fix applies mostly to unsupported terminals that do not trigger the
special interrupt handling in liner. Supported terminals were covered
because liner.Prompt returns an error if Ctrl-C is pressed.
2015-05-27 00:54:48 +02:00
612f01400f p2p/discover: bond with seed nodes too (runs only if findnode failed) 2015-05-26 23:30:41 +02:00
3630432dfb p2p/discovery: fix a cornercase loop if no seeds or bootnodes are known 2015-05-26 23:30:40 +02:00
f539ed1e66 p2p/discover: force refresh if the table is empty 2015-05-26 23:30:40 +02:00
5076170f34 p2p/discover: permit temporary bond failures for previously known nodes 2015-05-26 23:30:40 +02:00
6078aa08eb p2p/discover: watch find failures, evacuate on too many, rebond if failed 2015-05-26 23:30:40 +02:00
64174f196f p2p/discover: add support for counting findnode failures 2015-05-26 23:30:40 +02:00
6a674ffea5 Merge pull request #1108 from karalabe/fine-seeding
Fine tune seeder and p2p peer handling
2015-05-26 22:03:11 +02:00
b1f7b5d1f6 Merge pull request #1111 from obscuren/neg_tx_check
core: check negative value transactions. Closes #1109
2015-05-26 11:45:23 -07:00
c37389f19c core: check negative value transactions. Closes #1109 2015-05-26 20:38:26 +02:00
a55f408c10 Merge pull request #1090 from fjl/jsre-fixes
jsre: fixes for concurrent use, improved timer handling
2015-05-26 11:06:54 -07:00
39b1fe8e44 Merge pull request #1086 from debris/solidity_std
common/compiler: compile solidity contracts with std library
2015-05-26 10:58:09 -07:00
365eea9fba Merge pull request #1106 from karalabe/silence-useless-downloader-log
eth/downloader: silence "Added N blocks from..." if N == 0
2015-05-26 09:45:44 -07:00
4de8213887 cmd/geth: fix js console test for p2p server update 2015-05-26 19:35:31 +03:00
68898a4d6b p2p: fix Self() panic if listening is disabled 2015-05-26 19:16:05 +03:00
e1a0ee8fc5 cmd/geth, cmd/utils, eth, p2p: pass and honor a no discovery flag 2015-05-26 19:07:24 +03:00
278183c7e7 eth, p2p: start the p2p server even if maxpeers == 0 2015-05-26 17:49:37 +03:00
ceea1a7051 Merge branch 'develop' 2015-05-26 15:35:57 +02:00
eae0927597 core: prevent crash when last block fails 2015-05-26 15:35:51 +02:00
3083ec5e32 eth/downloader: silence "Added N blocks from..." if N == 0 2015-05-26 16:10:28 +03:00
2f2dd80e48 Merge branch 'develop' 2015-05-26 14:51:41 +02:00
d74ee40c86 cmd/geth: bumped version to 0.9.24 2015-05-26 14:51:28 +02:00
e6b143b00d Merge branch 'develop' 2015-05-26 14:50:37 +02:00
3386ecb59a Merge branch 'release/0.9.24' into develop 2015-05-26 14:49:06 +02:00
52b4e51366 Merge branch 'release/0.9.24' 2015-05-26 14:48:39 +02:00
0a85260bcd cmd/geth: bumped version to 0.9.24 2015-05-26 14:08:51 +02:00
245f30c59b Merge pull request #1014 from fjl/p2p-dialer-3000
p2p: new dialer, peer management without locks
2015-05-26 05:06:00 -07:00
fd38ea4149 Merge pull request #1099 from obscuren/fork_fix
Fork fix
2015-05-26 04:50:04 -07:00
6c2f6f5b03 tests: removed missing block test 2015-05-26 13:48:10 +02:00
a6b46420d0 core: ban hash 38f5bb...a714bc
Hash 38f5bbbffd74804820ffa4bab0cd540e9de229725afb98c1a7e57936f4a714bc
ignored.
2015-05-26 13:48:10 +02:00
f6f81169fe core/vm: Fork fix. Removal of appending 0 bytes in memset 2015-05-26 13:48:10 +02:00
03faccfb08 tests: updated 2015-05-26 13:48:10 +02:00
0de13b0bba Merge pull request #1102 from karalabe/maintain-block-origins
eth, eth/downloader: surface downloaded block origin, drop on error
2015-05-26 04:31:29 -07:00
eafdc1f8e3 eth, eth/downloader: surface downloaded block origin, drop on error 2015-05-26 14:00:21 +03:00
5044eb4b26 Merge pull request #1101 from obscuren/issue-1096
core/vm: Cleanups & SUB output fix. Closes #1096
2015-05-26 03:50:27 -07:00
b419e2631a core/vm: Cleanups & SUB output fix. Closes #1096 2015-05-26 12:42:33 +02:00
cc318ff8db Merge pull request #1078 from carver/patch-1
eth: expand acronym in log message from TD
2015-05-25 02:49:53 +02:00
e221a449e0 cmd/geth, jsre, rpc: run all JS code on the event loop
Some JSRE methods (PrettyPrint, ToVal) bypassed the event loop. All
calls to the JS VM are now wrapped. In order to make this somewhat more
foolproof, the otto VM is now a local variable inside the event loop.
2015-05-25 02:27:37 +02:00
9e1fd70b50 p2p: decrease frameReadTimeout to 30s
This detects hanging connections sooner. We send a ping every 15s and
other implementation have similar limits.
2015-05-25 01:17:14 +02:00
1440f9a37a p2p: new dialer, peer management without locks
The most visible change is event-based dialing, which should be an
improvement over the timer-based system that we have at the moment.
The dialer gets a chance to compute new tasks whenever peers change or
dials complete. This is better than checking peers on a timer because
dials happen faster. The dialer can now make more precise decisions
about whom to dial based on the peer set and we can test those
decisions without actually opening any sockets.

Peer management is easier to test because the tests can inject
connections at checkpoints (after enc handshake, after protocol
handshake).

Most of the handshake stuff is now part of the RLPx code. It could be
exported or move to its own package because it is no longer entangled
with Server logic.
2015-05-25 01:17:14 +02:00
9f38ef5d97 p2p/discover: add ReadRandomNodes 2015-05-25 01:17:14 +02:00
64564da20b p2p: decrease maximum message size for devp2p to 1kB
The previous limit was 10MB which is unacceptable for all kinds
of reasons, the most important one being that we don't want to
allow the remote side to make us allocate 10MB at handshake time.
2015-05-25 01:17:14 +02:00
7b93341836 Godeps: add github.com/davecgh/go-spew 2015-05-25 01:17:14 +02:00
dbdc5fd4b3 p2p: delete Server.Broadcast 2015-05-25 01:17:14 +02:00
2f249fea44 eth: stop p2p.Server on shutdown 2015-05-25 01:17:14 +02:00
394826f520 Merge pull request #1066 from karalabe/peer-db-polishes
p2p/discover: evacuate self from node database during iterations
2015-05-25 01:16:23 +02:00
c31f8e2bd7 compile solidity contracts with std library 2015-05-24 19:12:18 +02:00
f1ce5877ba do not export ring buffer struct 2015-05-23 12:09:59 -07:00
8a7fb5fd34 do not export constant for when to log a deep block you mined 2015-05-23 12:09:52 -07:00
97433f5ef1 expand acronym in log message from TD
to total difficulty
2015-05-22 19:12:59 -07:00
ba295ec6fe Log locally mined blocks, after they are 5-deep in the chain
This helps determine which blocks are unlikely to end up as uncles

 * Store the 5 most recent locally mined block numbers
 * On every imported block, check if the 5-deep block num is in that store
 * Also confirm that the block is signed with miner's coinbase

Why not just check the coinbase? This log is useful if you're running
multiple miners and want to know if *this* miner is performing well.
2015-05-22 12:53:32 -07:00
b2b9b3b567 Merge pull request #1077 from obscuren/disasm
core/vm, rpc: added disasm to `ext_` RPC
2015-05-22 06:51:38 -07:00
7381be8edb core/vm, rpc: added disasm to ext_ RPC 2015-05-22 15:38:46 +02:00
f7415c0bbc Merge pull request #1076 from obscuren/rpc_sign
core: added RPC sign back in
2015-05-22 04:08:51 -07:00
6539ccae7c core: added RPC sign back in 2015-05-22 13:00:04 +02:00
01ddaf5670 Merge pull request #1072 from Gustav-Simonsson/add_random_tests
Add StateTests/RandomTests and VMTests/RandomTests
2015-05-22 02:34:48 -07:00
f5e112ae5a Merge pull request #1074 from bas-vk/issue1068
make registrar available in console
2015-05-22 02:22:49 -07:00
821b578f7e make registrar available in console 2015-05-22 09:13:45 +02:00
6ad817e17b Add StateTests/RandomTests and VMTests/RandomTests 2015-05-21 23:04:46 +02:00
13e662f6de Merge branch 'develop' 2015-05-21 19:53:35 +02:00
054abe20b8 miner: moved break INSIDE the switch ... 2015-05-21 19:53:27 +02:00
8c25a83708 Merge branch 'release/0.9.23' into develop 2015-05-21 18:59:26 +02:00
2c1c78a6d9 Merge branch 'release/0.9.23' 2015-05-21 18:58:57 +02:00
cbd3ae6906 p2p/discover: fix #838, evacuate self entries from the node db 2015-05-21 19:41:46 +03:00
af24c271c7 p2p/discover: fix database presistency test folder 2015-05-21 19:28:10 +03:00
3ea9868b65 miner: on downloader.Done/Fail stop immediately. Ignore pending evs 2015-05-21 18:14:32 +02:00
4600ecb5c7 cmd/geth: bump version 0.9.23 2015-05-21 18:02:15 +02:00
f1cc3619f5 Merge pull request #1055 from ethersphere/autodag
automatic DAG pregeneration for smooth epoch transitions
2015-05-21 09:01:57 -07:00
af28736bd0 Merge pull request #1064 from karalabe/downloader-attacks
Fix two additional download vulnerabilities
2015-05-21 09:00:12 -07:00
06a041589f eth, eth/downloader: remove duplicate consts, bump hash fetch to 2K 2015-05-21 18:16:04 +03:00
bed80133e0 automatic DAG pregeneration for smooth epoch transitions
- backend: AutoDAG bool flag passed from cli/eth.Config to ethereum, autoDAG loop started if true
- backend: autoDAG loop start/stop, remove previous DAG
- cli: AutoDAG bool flag, off by default, but automatically ON if mining
- admin jsre: add startAutoDAG stopAutoDAG and makeDAG in miner section
- switch on/off DAG autogeneration when miner started/stopped on console
2015-05-21 15:53:42 +01:00
1da145675d Merge pull request #1063 from bas-vk/issue1053
prefix dapp key/value entries in extradb
2015-05-21 06:43:17 -07:00
a61e6788db prefix dapp key/value entries in extradb 2015-05-21 15:20:38 +02:00
90b672f1af Merge pull request #1062 from Gustav-Simonsson/tests_updates
Tests updates
2015-05-21 04:49:23 -07:00
bf7dcfce36 Merge pull request #1059 from obscuren/cleanup
Cleanup
2015-05-21 04:11:36 -07:00
907848997b miner: one-shot update loop 2015-05-21 11:57:00 +02:00
207bd55751 eth: reduced max open files for LevelDB 2015-05-21 11:45:35 +02:00
84cd618585 ethdb: documentation and corruption recovery 2015-05-21 11:43:05 +02:00
ef8744d9fc core: switched back to set.Set for uncle verification 2015-05-21 11:36:39 +02:00
ff1630834c xeth: removed Value 2015-05-21 11:36:05 +02:00
52db6d8be5 eth/downloader: circumvent a forged block chain with known parent attack 2015-05-21 08:37:27 +03:00
e8b22b9253 eth/downloader: prevent a peer from dripping bad hashes 2015-05-21 08:07:58 +03:00
9bde7fd72e Merge pull request #1043 from obscuren/test_fixes
core/vm: optimisation on RETURN and updated tests
2015-05-20 03:06:04 -07:00
8fe8ec84f6 Merge pull request #1049 from zsfelfoldi/receipts
Storing tx receipts in extraDb
2015-05-20 03:00:36 -07:00
0300eef94d Merge pull request #1048 from ethersphere/cli-fixes
CLI, JSRE admin and  Solc improvements
2015-05-20 02:31:52 -07:00
6b83a0a589 Merge pull request #1050 from karalabe/handle-slow-download-tester
eth/downloader: fix test to it doesn't time out on a slow machine
2015-05-20 02:29:23 -07:00
adaa49d2cc Merge pull request #1051 from karalabe/fix-odd-naming
eth: fix odd method names in peer set
2015-05-20 02:29:07 -07:00
3c8227b935 eth: fix odd method names in peer set 2015-05-20 10:34:45 +03:00
6f54eb6d9a eth/downloader: fix test to it doesn't time out on a slow machine 2015-05-20 10:15:42 +03:00
00ec4132f8 Storing tx receipts in extraDb 2015-05-20 06:41:50 +02:00
e1d1417729 rpc: NewNotAvailableError instead of NewNotImplementedError if no solc 2015-05-20 05:29:28 +01:00
00f59f5014 fix eth.sign. now implemented in admin jsre until web3.js has it . 2015-05-20 04:38:20 +01:00
b0ae84aa0d multiple contract source for solidity compiler: returns contract array if multiple contracts. fixes #1023 2015-05-20 04:11:48 +01:00
ea893aca8f update web3.js to 0.4.2 2015-05-20 02:58:49 +01:00
d92172f3d4 add usage doc to wallet import 2015-05-20 02:47:13 +01:00
4201a18117 remove solc flair 2015-05-20 02:47:13 +01:00
22b694ee1e solc now in ethereum, fixes solc path setting; setSolc() didnt work 2015-05-20 02:47:13 +01:00
f9abcee0f9 fix solc tests unskip 2015-05-20 02:47:13 +01:00
9617aa8e19 tests: added conditional skip on long running VM tests
Set the TEST_VM_COMPLEX env var to test complex vm tests which require a
lot of ram and quite some time.
2015-05-20 00:21:24 +02:00
f5af1fdca8 core/vm: RETURN op code returns pointer to memory rather than copy 2015-05-20 00:21:23 +02:00
648b352424 tests/vm: updated tests and skipped output for specific tests
Skipped tests due to large return value
2015-05-20 00:21:23 +02:00
79042223dc Merge pull request #1044 from obscuren/thread_safe_block_cache
core: block cache Has method thread safe
2015-05-19 15:11:41 -07:00
b14ee6ce16 Merge pull request #1046 from tgerring/issue1045
Allow unlocking multiple accounts
2015-05-19 15:11:20 -07:00
8dac28f2e3 core: block cache Has method thread safe 2015-05-19 21:50:56 +02:00
87a05c8f38 core: skipped tests while cache disabled 2015-05-19 21:50:26 +02:00
32b8565022 Support multiple account unlock attempts 2015-05-19 14:46:32 -05:00
af8ada45e7 Allow unlocking multiple accounts #1045
Separate accounts with spaces when using --unlock
2015-05-19 13:40:41 -05:00
46d6470c43 Merge pull request #1035 from karalabe/eth-threadsafe-peers
eth: make the peer-set thread safe
2015-05-19 08:50:38 -07:00
9b825e2728 Merge pull request #1036 from tgerring/issue884
JSON RPC null field updates
2015-05-19 06:44:31 -07:00
748263d2f0 Use bytes.Repeat() instead of 32-byte literal 2015-05-19 08:14:48 -05:00
7d9a13e0d5 core: disable cash tmp 2015-05-19 12:59:58 +02:00
6c2ad7b72e Merge pull request #1034 from obscuren/tx_pool_fix
Nonce fix for failing transactions
2015-05-18 12:28:51 -07:00
b7baceefda xeth: remove nonce on error. Fixes #1026 2015-05-18 20:52:25 +02:00
4755caeb2d eth: remote a superfluous peerSet method 2015-05-18 21:35:42 +03:00
5422fe5125 eth: make the peer set thread safe 2015-05-18 21:33:37 +03:00
bd0c0a633b Merge pull request #1022 from obscuren/parallel_nonce_checks
Parallelise nonce checks
2015-05-18 11:13:53 -07:00
d6adadc5e3 Merge pull request #1033 from tgerring/issue1010
Add "removedb" command to Geth
2015-05-18 11:12:58 -07:00
0864f1fc8e Remove unused confirm() method 2015-05-18 12:25:33 -05:00
f14feea436 Refactor user prompts into utils 2015-05-18 12:24:30 -05:00
36a4ba3248 Add user confirmation for removedb 2015-05-18 12:04:35 -05:00
40717465bc core: fixed tests 2015-05-18 18:16:53 +02:00
59c0d01418 core: chain manager no longer exports genesis block 2015-05-18 18:16:53 +02:00
bc5e60cd63 miner: stale block notification 2015-05-18 18:16:53 +02:00
fe41bd6fe8 Add "removedb" command to Geth
Removes the state and blockchain databases
2015-05-18 10:54:15 -05:00
a3a5f8b593 Merge pull request #1032 from tgerring/issue1025
Multiple CORS domains support
2015-05-18 08:49:35 -07:00
54b5c8273d XEth comment clarification 2015-05-18 10:41:56 -05:00
a2598e649d Permit multiple CORS domains
Separated by spaces
2015-05-18 10:31:03 -05:00
62d76b8e1f Cleanup 2015-05-18 10:11:27 -05:00
a528bd04db Return nil for certain fields on eth_getTransactionByHash when not part of a block 2015-05-18 10:09:00 -05:00
677796b351 Merge pull request #1031 from bas-vk/issue1012
fixed race condition in miner
2015-05-18 07:33:06 -07:00
6a72cd45e2 Add wrapper for BlockTests/bcWalletTest.json 2015-05-18 16:28:54 +02:00
1d51cada3c Handle call depth exception for CREATE 2015-05-18 16:23:20 +02:00
d381d9a74c Return nil for certain fields on eth_getBlockByNumber pending 2015-05-18 09:16:10 -05:00
60561cdca2 fixed issue when miner is not stopping af stop command 2015-05-18 16:09:01 +02:00
7778740315 fixed race condition in miner 2015-05-18 15:13:58 +02:00
c67424ecc8 core: parallelise nonce checking when processing blocks
ChainManager now uses a parallel approach to block processing where all
nonces are checked seperatly from the block processing process. This
speeds up the process by about 3 times on my i7
2015-05-18 13:59:22 +02:00
36419defd1 Update Ethereum JSON test files 2015-05-18 12:45:24 +02:00
67d44519ce core: bugfix test 2. set => hash map 2015-05-18 10:49:09 +02:00
54f0f82dd1 ret 2015-05-18 10:14:48 +02:00
e323f0e831 core: tmp diagnostic logs 2015-05-18 10:13:50 +02:00
280b7f23af Merge branch 'hotfix/0.9.22' into develop 2015-05-17 21:35:29 +02:00
915fc0e581 Merge branch 'hotfix/0.9.22' 2015-05-17 21:35:15 +02:00
3a51d5e80c cmd/geth: fixed ver num 2015-05-17 21:34:28 +02:00
443d024843 Merge pull request #1021 from obscuren/global_chain_lock
core: global chain insert lock
2015-05-17 08:54:16 -07:00
27782bbade core: global chain insert lock 2015-05-17 00:55:02 +02:00
426c70ac0b Merge pull request #1011 from obscuren/upgradedb_fix
cmd/geth: delete state db on upgradedb command
2015-05-16 08:48:49 -07:00
28ba374f27 cmd/geth: delete state db on upgradedb command 2015-05-16 17:43:19 +02:00
ad99089567 Merge branch 'hotfix/0.9.21.1' into develop 2015-05-16 13:04:43 +02:00
69f8a1b01a Merge branch 'hotfix/0.9.21-1' 2015-05-16 13:03:30 +02:00
ad7b0efbd3 cmd/geth: hotfix bump 2015-05-16 13:02:30 +02:00
d98a6f85fc core: further improved uncle error messages 2015-05-16 13:02:30 +02:00
c2ef8682fe eth/downloader: moved start event
Start event has moved because it could possibly could stall the miner
2015-05-16 13:02:30 +02:00
fe64a13cea Adjust miner coinbase and not just miner worker coinbase 2015-05-16 12:56:06 +02:00
741fa8ca9c miner: mutex locks on cpu agent. Closes #1007 2015-05-16 12:55:56 +02:00
61e8296bd8 Adjust miner coinbase and not just miner worker coinbase 2015-05-15 21:23:09 -04:00
4b2ee6c30c Merge branch 'release/0.9.21' into develop 2015-05-16 00:27:35 +02:00
1564f1a020 Merge branch 'release/0.9.21' 2015-05-16 00:27:13 +02:00
7ea76fcf99 core, cmd/geth, cmd/mist: cleanup. bump version 0.9.21 2015-05-16 00:26:36 +02:00
79fa05867f xeth: set balance max balance to from in call. Closes #951 2015-05-16 00:03:08 +02:00
d116b9595c Merge pull request #989 from obscuren/develop
core, miner: fork resolving and restart miner after sync op
2015-05-15 15:02:22 -07:00
55d85d60fd eth, cmd/geth: start mining from console respects CLI flag 2015-05-15 20:26:15 +02:00
d3e84cc8b4 miner: properly check for mining operation on Register 2015-05-15 20:26:15 +02:00
5cec1aad15 core, miner: fork resolving and restart miner after sync op
Fork resolving fixes #940
2015-05-15 20:26:15 +02:00
82c0780f81 Merge pull request #996 from karalabe/fix-potential-crosscheck-race
eth/downloader: circumvent download race between crosscheck and hashes
2015-05-15 11:23:44 -07:00
cea1723c68 Merge pull request #997 from karalabe/fix-shitty-test-server-issue
eth/downloader: fix #992, where tests may time out on a slow machine
2015-05-15 11:22:51 -07:00
412cf98bbc eth/downloader: fix #992, where tests may time out on a slow machine 2015-05-15 21:16:42 +03:00
f3ae8f50a5 eth/downloader: circumvent download race between crosscheck and hashes 2015-05-15 20:54:10 +03:00
98998534cb Merge pull request #995 from Gustav-Simonsson/update_state_tests_and_vm_create_return
Update state tests and vm create return
2015-05-15 10:31:41 -07:00
619e8a4f03 Add StateTests/RandomTests but skip for now 2015-05-15 19:17:40 +02:00
164ba56a60 Merge pull request #994 from karalabe/fix-cancel-double-close
eth/downloader: fix cancel channel double close
2015-05-15 10:15:35 -07:00
32276e8b01 Update StateTests and nil create return on failed code deposit 2015-05-15 18:49:31 +02:00
4f0d88cb02 eth/downloader: fix cancel channel double close 2015-05-15 19:43:42 +03:00
830bdb1cfd Update Ethereum JSON tests 2015-05-15 16:08:00 +02:00
dadf01de60 unskip StateTests/stTransactionTest and use test tx nonce 2015-05-15 16:05:11 +02:00
7d71a75d77 Merge pull request #988 from karalabe/fix-downloader-vulnerabilities
Fix downloader vulnerabilities
2015-05-15 06:38:12 -07:00
5c1a7b965c eth/downloader: circumvent a fake blockchain attack 2015-05-15 15:04:15 +03:00
b517967f86 eth/downloader: don't penalize for stale cross checks 2015-05-15 15:03:08 +03:00
83226762c2 eth, eth/downloader: detect and handle madeup hash attacks 2015-05-15 15:01:58 +03:00
9ad515d2dc eth: drop a sync peer if it sends an invalid hash chain 2015-05-15 15:01:58 +03:00
72411eb24c eth/downloader: circumvent hash reordering attacks 2015-05-15 15:01:58 +03:00
bcc2980179 eth/downloader: check sync after failed attacks 2015-05-15 15:01:58 +03:00
366e9627e8 eth/downloader: add a test for detecting missing blocks 2015-05-15 15:01:58 +03:00
cd2fb09051 eth, eth/downloader: prevent hash repeater attack 2015-05-15 15:01:58 +03:00
c1f0d40e34 Merge pull request #987 from obscuren/develop
Miner updates and downloader events
2015-05-15 04:12:46 -07:00
158efbaa45 Merge pull request #984 from tgerring/issue924
Omit replies for RPC notification requests
2015-05-15 04:12:40 -07:00
cfb2b51b74 eth/downloader: fixed test 2015-05-15 12:47:32 +02:00
f6669db001 core: fixed mining strategy 2015-05-15 12:24:29 +02:00
b71091e337 eth, eth/downloader, miner: use download events to check miner start 2015-05-15 00:43:10 +02:00
0f76a1c6df core: changed how head events are checked 2015-05-15 00:42:06 +02:00
580bae0a86 core: improved uncle messages 2015-05-15 00:40:07 +02:00
44a7f997c3 Unreverse ordering 2015-05-14 15:50:39 -05:00
5c6540452a Omit replies for notification requests
When Id is missing, the client does not want a response
2015-05-14 12:39:57 -05:00
3ac34ee3c4 Merge pull request #975 from obscuren/develop
core: changed log message for forks. closes #952
2015-05-14 10:38:10 -07:00
69c78ddbb4 Merge pull request #983 from tgerring/issue958
Format contract code as hexdata
2015-05-14 10:38:01 -07:00
007bced276 Merge pull request #982 from tgerring/issue962
Check for error on DB fetch of tx
2015-05-14 10:37:30 -07:00
6bc8dec7ac Merge pull request #980 from fjl/geth-test-no-scrypt
cmd/geth: use plain keystore for JS tests
2015-05-14 10:36:56 -07:00
4ad8f1035b Format contract code as hexdata 2015-05-14 12:17:19 -05:00
12f82ab2ff Check for error on DB fetch of tx 2015-05-14 11:57:29 -05:00
559cc02313 cmd/geth: use plain keystore for JS tests
This reduces the time it takes to run the tests back to 3 seconds.
2015-05-14 17:51:05 +02:00
b19bf3ec78 core: changed log message for forks. closes #952 2015-05-14 17:16:46 +02:00
060a07cf69 Merge pull request #974 from karalabe/downloader-fix-unknown-parent-attack
eth, eth/downloader: handle a potential unknown parent attack
2015-05-14 08:16:30 -07:00
90b94e64fc Merge pull request #971 from fjl/p2p-limit-tweaks
p2p: tweak connection limits
2015-05-14 08:15:51 -07:00
d2f119cf9b p2p/discover: limit open files for node database 2015-05-14 15:01:13 +02:00
206fe25971 p2p: remove testlog 2015-05-14 14:56:34 +02:00
7fa2607bd1 p2p/discover: bump maxBondingPingPongs to 16
This should increase the speed a bit because all findnode
results (up to 16) can be verified at the same time.
2015-05-14 14:53:29 +02:00
691cb90284 p2p: log remote reason when disconnect is requested
The returned reason is currently not used except for the log
message. This change makes the log messages a bit more useful.
The handshake code also returns the remote reason.
2015-05-14 14:53:29 +02:00
ff87c241a7 Merge pull request #973 from bas-vk/issue972
Introduced default unlock duration when an account is unlocked from t…
2015-05-14 05:48:31 -07:00
fe87feccb1 eth/downloader: add a small additional check to the test 2015-05-14 15:44:54 +03:00
ebf1eb9359 eth/downloader: remove a previous leftover 2015-05-14 15:40:28 +03:00
3eda70c64c eth, eth/downloader: remove parent verification from the downlaoder 2015-05-14 15:38:49 +03:00
1fa48bc5e7 Introduced default unlock duration when an account is unlocked from the console 2015-05-14 14:25:48 +02:00
a4246c2da6 eth, eth/downloader: handle a potential unknown parent attack 2015-05-14 15:24:18 +03:00
7fa740996c Merge pull request #960 from fjl/nat-fixes
p2p/nat: fix UPnP auto discovery
2015-05-14 04:06:13 -07:00
c7a13c9be8 Merge pull request #969 from Gustav-Simonsson/ethash_improve_hashrate_update2
Make read of ethash hashrate atomic and update ethash godep
2015-05-14 04:05:27 -07:00
2b06fe3eff Merge pull request #950 from karalabe/downloader-cancel-sync
eth/downloader: fix deliveries to check for sync cancels
2015-05-14 04:05:13 -07:00
cdeae22356 Merge pull request #949 from bas-vk/issue944
removed invalid filename characters
2015-05-14 04:04:43 -07:00
5f706cd7f5 cmd/utils: print messages from package log through glog
Some of the dependencies use package log. This change ensures that the
log output looks uniform and respects glog flags.
2015-05-14 12:56:37 +02:00
c14de2e973 p2p/nat: tweak port mapping log messages and levels
People stil get confused about the messages. This commit changes
the levels so that the only thing printed at the default level (info)
is a successful mapping.
2015-05-14 12:54:59 +02:00
e4aa011d23 Merge pull request #970 from ethereum/vitalik_quick_test
Created separate family and ancestors environment objects
2015-05-14 03:53:04 -07:00
e7c7b54b82 Godeps: bump github.com/huin/goupnp to c57ae84 2015-05-14 12:29:41 +02:00
663d4e0aff p2p/nat: add test for UPnP auto discovery via SSDP
The test listens for multicast UDP packets on the default interface
because I couldn't get it to work reliably on loopback without massive
changes to goupnp. This means that the test might fail when there is a
UPnP-enabled router attached on that interface. I checked that locally
by looping the test and it passes reliably because the local SSDP server
always responds faster.
2015-05-14 12:13:19 +02:00
bdec8c3e41 Combined two loops 2015-05-14 05:02:15 -04:00
b24f16fa53 Make read of ethash hashrate atomic and update ethash godep 2015-05-14 04:05:49 +02:00
983f5a717a p2p/nat: fix concurrent access to autodisc Interface
Concurrent calls to Interface methods on autodisc could return a "not
discovered" error if the discovery did not finish before the call.
autodisc.wait expected the done channel to carry the found Interface
but it was closed instead.

The fix is to use sync.Once for now, which is easier to get right.
And there is a test. Finally.

This will have to change again when we introduce re-discovery.
2015-05-14 03:53:11 +02:00
7efeb4bd96 p2p: bump maxAcceptConns and defaultDialTimout
On the test network, we've seen that it becomes harder to connect
if the queues are so short.
2015-05-14 03:48:28 +02:00
fca3333f7f Created separate family and ancestors environment objects 2015-05-13 20:46:23 -04:00
bc83761996 Fixed max uncle count error message 2015-05-13 20:29:57 -04:00
f7fdb4dfbe Merge pull request #966 from fjl/fixup-discover-chunked-neighbors
p2p/discover: fix out-of-bounds slicing for chunked neighbors packets
2015-05-13 21:52:58 +02:00
251846d65a p2p/discover: fix out-of-bounds slicing for chunked neighbors packets
The code assumed that Table.closest always returns at least 13 nodes.
This is not true for small tables (e.g. during bootstrap).
2015-05-13 21:49:04 +02:00
fad21fb4a5 Merge pull request #963 from Gustav-Simonsson/fix_keystore_crypto_comments
Update keystore code comments
2015-05-13 11:51:02 -07:00
b2119d8931 Merge pull request #965 from subtly/patch-1
Better UDP & interop. Limit all received datagrams to 1280bytes.
2015-05-13 20:34:10 +02:00
8eef2b765a fix test. 2015-05-13 20:15:01 +02:00
a32693770c Manual send of multiple neighbours packets. Test receiving multiple neighbours packets. 2015-05-13 20:03:17 +02:00
7473c93668 UDP Interop. Limit datagrams to 1280bytes.
We don't have a UDP which specifies any messages that will be 4KB. Aside from being implemented for months and a necessity for encryption and piggy-backing packets, 1280bytes is ideal, and, means this TODO can be completed!

Why 1280 bytes?
* It's less than the default MTU for most WAN/LAN networks. That means fewer fragmented datagrams (esp on well-connected networks).
* Fragmented datagrams and dropped packets suck and add latency while OS waits for a dropped fragment to never arrive (blocking readLoop())
* Most of our packets are < 1280 bytes.
* 1280 bytes is minimum datagram size and MTU for IPv6 -- on IPv6, a datagram < 1280bytes will *never* be fragmented.

UDP datagrams are dropped. A lot! And fragmented datagrams are worse. If a datagram has a 30% chance of being dropped, then a fragmented datagram has a 60% chance of being dropped. More importantly, we have signed packets and can't do anything with a packet unless we receive the entire datagram because the signature can't be verified. The same is true when we have encrypted packets.

So the solution here to picking an ideal buffer size for receiving datagrams is a number under 1400bytes. And the lower-bound value for IPv6 of 1280 bytes make's it a non-decision. On IPv4 most ISPs and 3g/4g/let networks have an MTU just over 1400 -- and *never* over 1500. Never -- that means packets over 1500 (in reality: ~1450) bytes are fragmented. And probably dropped a lot.

Just to prove the point, here are pings sending non-fragmented packets over wifi/ISP, and a second set of pings via cell-phone tethering. It's important to note that, if *any* router between my system and the EC2 node has a lower MTU, the message would not go through:

On wifi w/normal ISP:
localhost:Debug $ ping -D -s 1450 52.6.250.242
PING 52.6.250.242 (52.6.250.242): 1450 data bytes
1458 bytes from 52.6.250.242: icmp_seq=0 ttl=42 time=104.831 ms
1458 bytes from 52.6.250.242: icmp_seq=1 ttl=42 time=119.004 ms
^C
--- 52.6.250.242 ping statistics ---
2 packets transmitted, 2 packets received, 0.0% packet loss
round-trip min/avg/max/stddev = 104.831/111.918/119.004/7.087 ms
localhost:Debug $ ping -D -s 1480 52.6.250.242
PING 52.6.250.242 (52.6.250.242): 1480 data bytes
ping: sendto: Message too long
ping: sendto: Message too long
Request timeout for icmp_seq 0
ping: sendto: Message too long
Request timeout for icmp_seq 1


Tethering to O2:
localhost:Debug $ ping -D -s 1480 52.6.250.242
PING 52.6.250.242 (52.6.250.242): 1480 data bytes
ping: sendto: Message too long
ping: sendto: Message too long
Request timeout for icmp_seq 0
^C
--- 52.6.250.242 ping statistics ---
2 packets transmitted, 0 packets received, 100.0% packet loss
localhost:Debug $ ping -D -s 1450 52.6.250.242
PING 52.6.250.242 (52.6.250.242): 1450 data bytes
1458 bytes from 52.6.250.242: icmp_seq=0 ttl=42 time=107.844 ms
1458 bytes from 52.6.250.242: icmp_seq=1 ttl=42 time=105.127 ms
1458 bytes from 52.6.250.242: icmp_seq=2 ttl=42 time=120.483 ms
1458 bytes from 52.6.250.242: icmp_seq=3 ttl=42 time=102.136 ms
2015-05-13 19:03:00 +02:00
56a5592ea0 Update keystore code comments 2015-05-13 18:33:31 +02:00
3edc4698fe Merge pull request #954 from karalabe/fix-downloader-nil-panic
eth/downloader: fix nil panic caused by wrong variable use
2015-05-13 18:15:18 +02:00
910a6d4e46 eth/downloader: fix nil panic caused by wrong variable use 2015-05-13 17:25:01 +03:00
de3a71cafd eth/downloader: remove a redundant sync progress check 2015-05-13 16:56:01 +03:00
48ee0777a5 eth/downloader: add a user sync notificaton 2015-05-13 16:03:05 +03:00
ec57aa64cd eth/downloader: sync the cancel channel during cancel too 2015-05-13 14:01:08 +03:00
ee0c892303 eth/downloader: fix deliveries to check for sync cancels 2015-05-13 13:47:21 +03:00
7cb0e24245 Merge pull request #948 from karalabe/fix-downlaoder-activepeer-shadow
eth/downloader: fix active peer shadowing, polish func names
2015-05-13 03:46:29 -07:00
e30e9fe979 removed invalid filename characters 2015-05-13 12:38:12 +02:00
d2d5dbc6fb eth/downloader: fix active peer shadowing, polish func names 2015-05-13 13:13:43 +03:00
6dec90464d Merge pull request #946 from Gustav-Simonsson/fix_geth_unlock_account
Fix hex conversion in --unlock and log when successful
2015-05-13 01:58:32 -07:00
b5b53d8b32 Fix hex conversion in --unlock and log when successful 2015-05-13 01:11:17 +02:00
28d6b30c0f Merge branch 'release/0.9.20' into develop 2015-05-12 19:05:51 +02:00
259 changed files with 633804 additions and 7026 deletions

22
Godeps/Godeps.json generated
View File

@ -15,10 +15,14 @@
"Comment": "1.2.0-95-g9b2bd2b", "Comment": "1.2.0-95-g9b2bd2b",
"Rev": "9b2bd2b3489748d4d0a204fa4eb2ee9e89e0ebc6" "Rev": "9b2bd2b3489748d4d0a204fa4eb2ee9e89e0ebc6"
}, },
{
"ImportPath": "github.com/davecgh/go-spew/spew",
"Rev": "3e6e67c4dcea3ac2f25fd4731abc0e1deaf36216"
},
{ {
"ImportPath": "github.com/ethereum/ethash", "ImportPath": "github.com/ethereum/ethash",
"Comment": "v23.1-204-g0401fdf", "Comment": "v23.1-206-gf0e6321",
"Rev": "0401fdf56a3bc8679f9560e542c3d1cf83020efe" "Rev": "f0e63218b721dc2f696920a92d5de1f6364e9bf7"
}, },
{ {
"ImportPath": "github.com/howeyc/fsnotify", "ImportPath": "github.com/howeyc/fsnotify",
@ -27,7 +31,7 @@
}, },
{ {
"ImportPath": "github.com/huin/goupnp", "ImportPath": "github.com/huin/goupnp",
"Rev": "4191d8a85005844ea202fde52799681971b12dfe" "Rev": "c57ae84388ab59076fd547f1abeab71c2edb0a21"
}, },
{ {
"ImportPath": "github.com/jackpal/go-nat-pmp", "ImportPath": "github.com/jackpal/go-nat-pmp",
@ -89,6 +93,18 @@
"ImportPath": "golang.org/x/crypto/scrypt", "ImportPath": "golang.org/x/crypto/scrypt",
"Rev": "4ed45ec682102c643324fae5dff8dab085b6c300" "Rev": "4ed45ec682102c643324fae5dff8dab085b6c300"
}, },
{
"ImportPath": "golang.org/x/net/html",
"Rev": "e0403b4e005737430c05a57aac078479844f919c"
},
{
"ImportPath": "golang.org/x/text/encoding",
"Rev": "c93e7c9fff19fb9139b5ab04ce041833add0134e"
},
{
"ImportPath": "golang.org/x/text/transform",
"Rev": "c93e7c9fff19fb9139b5ab04ce041833add0134e"
},
{ {
"ImportPath": "gopkg.in/check.v1", "ImportPath": "gopkg.in/check.v1",
"Rev": "64131543e7896d5bcc6bd5a76287eb75ea96c673" "Rev": "64131543e7896d5bcc6bd5a76287eb75ea96c673"

View File

@ -0,0 +1,450 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew
import (
"bytes"
"fmt"
"io"
"reflect"
"sort"
"strconv"
"unsafe"
)
const (
// ptrSize is the size of a pointer on the current arch.
ptrSize = unsafe.Sizeof((*byte)(nil))
)
var (
// offsetPtr, offsetScalar, and offsetFlag are the offsets for the
// internal reflect.Value fields. These values are valid before golang
// commit ecccf07e7f9d which changed the format. The are also valid
// after commit 82f48826c6c7 which changed the format again to mirror
// the original format. Code in the init function updates these offsets
// as necessary.
offsetPtr = uintptr(ptrSize)
offsetScalar = uintptr(0)
offsetFlag = uintptr(ptrSize * 2)
// flagKindWidth and flagKindShift indicate various bits that the
// reflect package uses internally to track kind information.
//
// flagRO indicates whether or not the value field of a reflect.Value is
// read-only.
//
// flagIndir indicates whether the value field of a reflect.Value is
// the actual data or a pointer to the data.
//
// These values are valid before golang commit 90a7c3c86944 which
// changed their positions. Code in the init function updates these
// flags as necessary.
flagKindWidth = uintptr(5)
flagKindShift = uintptr(flagKindWidth - 1)
flagRO = uintptr(1 << 0)
flagIndir = uintptr(1 << 1)
)
func init() {
// Older versions of reflect.Value stored small integers directly in the
// ptr field (which is named val in the older versions). Versions
// between commits ecccf07e7f9d and 82f48826c6c7 added a new field named
// scalar for this purpose which unfortunately came before the flag
// field, so the offset of the flag field is different for those
// versions.
//
// This code constructs a new reflect.Value from a known small integer
// and checks if the size of the reflect.Value struct indicates it has
// the scalar field. When it does, the offsets are updated accordingly.
vv := reflect.ValueOf(0xf00)
if unsafe.Sizeof(vv) == (ptrSize * 4) {
offsetScalar = ptrSize * 2
offsetFlag = ptrSize * 3
}
// Commit 90a7c3c86944 changed the flag positions such that the low
// order bits are the kind. This code extracts the kind from the flags
// field and ensures it's the correct type. When it's not, the flag
// order has been changed to the newer format, so the flags are updated
// accordingly.
upf := unsafe.Pointer(uintptr(unsafe.Pointer(&vv)) + offsetFlag)
upfv := *(*uintptr)(upf)
flagKindMask := uintptr((1<<flagKindWidth - 1) << flagKindShift)
if (upfv&flagKindMask)>>flagKindShift != uintptr(reflect.Int) {
flagKindShift = 0
flagRO = 1 << 5
flagIndir = 1 << 6
}
}
// unsafeReflectValue converts the passed reflect.Value into a one that bypasses
// the typical safety restrictions preventing access to unaddressable and
// unexported data. It works by digging the raw pointer to the underlying
// value out of the protected value and generating a new unprotected (unsafe)
// reflect.Value to it.
//
// This allows us to check for implementations of the Stringer and error
// interfaces to be used for pretty printing ordinarily unaddressable and
// inaccessible values such as unexported struct fields.
func unsafeReflectValue(v reflect.Value) (rv reflect.Value) {
indirects := 1
vt := v.Type()
upv := unsafe.Pointer(uintptr(unsafe.Pointer(&v)) + offsetPtr)
rvf := *(*uintptr)(unsafe.Pointer(uintptr(unsafe.Pointer(&v)) + offsetFlag))
if rvf&flagIndir != 0 {
vt = reflect.PtrTo(v.Type())
indirects++
} else if offsetScalar != 0 {
// The value is in the scalar field when it's not one of the
// reference types.
switch vt.Kind() {
case reflect.Uintptr:
case reflect.Chan:
case reflect.Func:
case reflect.Map:
case reflect.Ptr:
case reflect.UnsafePointer:
default:
upv = unsafe.Pointer(uintptr(unsafe.Pointer(&v)) +
offsetScalar)
}
}
pv := reflect.NewAt(vt, upv)
rv = pv
for i := 0; i < indirects; i++ {
rv = rv.Elem()
}
return rv
}
// Some constants in the form of bytes to avoid string overhead. This mirrors
// the technique used in the fmt package.
var (
panicBytes = []byte("(PANIC=")
plusBytes = []byte("+")
iBytes = []byte("i")
trueBytes = []byte("true")
falseBytes = []byte("false")
interfaceBytes = []byte("(interface {})")
commaNewlineBytes = []byte(",\n")
newlineBytes = []byte("\n")
openBraceBytes = []byte("{")
openBraceNewlineBytes = []byte("{\n")
closeBraceBytes = []byte("}")
asteriskBytes = []byte("*")
colonBytes = []byte(":")
colonSpaceBytes = []byte(": ")
openParenBytes = []byte("(")
closeParenBytes = []byte(")")
spaceBytes = []byte(" ")
pointerChainBytes = []byte("->")
nilAngleBytes = []byte("<nil>")
maxNewlineBytes = []byte("<max depth reached>\n")
maxShortBytes = []byte("<max>")
circularBytes = []byte("<already shown>")
circularShortBytes = []byte("<shown>")
invalidAngleBytes = []byte("<invalid>")
openBracketBytes = []byte("[")
closeBracketBytes = []byte("]")
percentBytes = []byte("%")
precisionBytes = []byte(".")
openAngleBytes = []byte("<")
closeAngleBytes = []byte(">")
openMapBytes = []byte("map[")
closeMapBytes = []byte("]")
lenEqualsBytes = []byte("len=")
capEqualsBytes = []byte("cap=")
)
// hexDigits is used to map a decimal value to a hex digit.
var hexDigits = "0123456789abcdef"
// catchPanic handles any panics that might occur during the handleMethods
// calls.
func catchPanic(w io.Writer, v reflect.Value) {
if err := recover(); err != nil {
w.Write(panicBytes)
fmt.Fprintf(w, "%v", err)
w.Write(closeParenBytes)
}
}
// handleMethods attempts to call the Error and String methods on the underlying
// type the passed reflect.Value represents and outputes the result to Writer w.
//
// It handles panics in any called methods by catching and displaying the error
// as the formatted value.
func handleMethods(cs *ConfigState, w io.Writer, v reflect.Value) (handled bool) {
// We need an interface to check if the type implements the error or
// Stringer interface. However, the reflect package won't give us an
// interface on certain things like unexported struct fields in order
// to enforce visibility rules. We use unsafe to bypass these restrictions
// since this package does not mutate the values.
if !v.CanInterface() {
v = unsafeReflectValue(v)
}
// Choose whether or not to do error and Stringer interface lookups against
// the base type or a pointer to the base type depending on settings.
// Technically calling one of these methods with a pointer receiver can
// mutate the value, however, types which choose to satisify an error or
// Stringer interface with a pointer receiver should not be mutating their
// state inside these interface methods.
var viface interface{}
if !cs.DisablePointerMethods {
if !v.CanAddr() {
v = unsafeReflectValue(v)
}
viface = v.Addr().Interface()
} else {
if v.CanAddr() {
v = v.Addr()
}
viface = v.Interface()
}
// Is it an error or Stringer?
switch iface := viface.(type) {
case error:
defer catchPanic(w, v)
if cs.ContinueOnMethod {
w.Write(openParenBytes)
w.Write([]byte(iface.Error()))
w.Write(closeParenBytes)
w.Write(spaceBytes)
return false
}
w.Write([]byte(iface.Error()))
return true
case fmt.Stringer:
defer catchPanic(w, v)
if cs.ContinueOnMethod {
w.Write(openParenBytes)
w.Write([]byte(iface.String()))
w.Write(closeParenBytes)
w.Write(spaceBytes)
return false
}
w.Write([]byte(iface.String()))
return true
}
return false
}
// printBool outputs a boolean value as true or false to Writer w.
func printBool(w io.Writer, val bool) {
if val {
w.Write(trueBytes)
} else {
w.Write(falseBytes)
}
}
// printInt outputs a signed integer value to Writer w.
func printInt(w io.Writer, val int64, base int) {
w.Write([]byte(strconv.FormatInt(val, base)))
}
// printUint outputs an unsigned integer value to Writer w.
func printUint(w io.Writer, val uint64, base int) {
w.Write([]byte(strconv.FormatUint(val, base)))
}
// printFloat outputs a floating point value using the specified precision,
// which is expected to be 32 or 64bit, to Writer w.
func printFloat(w io.Writer, val float64, precision int) {
w.Write([]byte(strconv.FormatFloat(val, 'g', -1, precision)))
}
// printComplex outputs a complex value using the specified float precision
// for the real and imaginary parts to Writer w.
func printComplex(w io.Writer, c complex128, floatPrecision int) {
r := real(c)
w.Write(openParenBytes)
w.Write([]byte(strconv.FormatFloat(r, 'g', -1, floatPrecision)))
i := imag(c)
if i >= 0 {
w.Write(plusBytes)
}
w.Write([]byte(strconv.FormatFloat(i, 'g', -1, floatPrecision)))
w.Write(iBytes)
w.Write(closeParenBytes)
}
// printHexPtr outputs a uintptr formatted as hexidecimal with a leading '0x'
// prefix to Writer w.
func printHexPtr(w io.Writer, p uintptr) {
// Null pointer.
num := uint64(p)
if num == 0 {
w.Write(nilAngleBytes)
return
}
// Max uint64 is 16 bytes in hex + 2 bytes for '0x' prefix
buf := make([]byte, 18)
// It's simpler to construct the hex string right to left.
base := uint64(16)
i := len(buf) - 1
for num >= base {
buf[i] = hexDigits[num%base]
num /= base
i--
}
buf[i] = hexDigits[num]
// Add '0x' prefix.
i--
buf[i] = 'x'
i--
buf[i] = '0'
// Strip unused leading bytes.
buf = buf[i:]
w.Write(buf)
}
// valuesSorter implements sort.Interface to allow a slice of reflect.Value
// elements to be sorted.
type valuesSorter struct {
values []reflect.Value
strings []string // either nil or same len and values
cs *ConfigState
}
// newValuesSorter initializes a valuesSorter instance, which holds a set of
// surrogate keys on which the data should be sorted. It uses flags in
// ConfigState to decide if and how to populate those surrogate keys.
func newValuesSorter(values []reflect.Value, cs *ConfigState) sort.Interface {
vs := &valuesSorter{values: values, cs: cs}
if canSortSimply(vs.values[0].Kind()) {
return vs
}
if !cs.DisableMethods {
vs.strings = make([]string, len(values))
for i := range vs.values {
b := bytes.Buffer{}
if !handleMethods(cs, &b, vs.values[i]) {
vs.strings = nil
break
}
vs.strings[i] = b.String()
}
}
if vs.strings == nil && cs.SpewKeys {
vs.strings = make([]string, len(values))
for i := range vs.values {
vs.strings[i] = Sprintf("%#v", vs.values[i].Interface())
}
}
return vs
}
// canSortSimply tests whether a reflect.Kind is a primitive that can be sorted
// directly, or whether it should be considered for sorting by surrogate keys
// (if the ConfigState allows it).
func canSortSimply(kind reflect.Kind) bool {
// This switch parallels valueSortLess, except for the default case.
switch kind {
case reflect.Bool:
return true
case reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64, reflect.Int:
return true
case reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uint:
return true
case reflect.Float32, reflect.Float64:
return true
case reflect.String:
return true
case reflect.Uintptr:
return true
case reflect.Array:
return true
}
return false
}
// Len returns the number of values in the slice. It is part of the
// sort.Interface implementation.
func (s *valuesSorter) Len() int {
return len(s.values)
}
// Swap swaps the values at the passed indices. It is part of the
// sort.Interface implementation.
func (s *valuesSorter) Swap(i, j int) {
s.values[i], s.values[j] = s.values[j], s.values[i]
if s.strings != nil {
s.strings[i], s.strings[j] = s.strings[j], s.strings[i]
}
}
// valueSortLess returns whether the first value should sort before the second
// value. It is used by valueSorter.Less as part of the sort.Interface
// implementation.
func valueSortLess(a, b reflect.Value) bool {
switch a.Kind() {
case reflect.Bool:
return !a.Bool() && b.Bool()
case reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64, reflect.Int:
return a.Int() < b.Int()
case reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uint:
return a.Uint() < b.Uint()
case reflect.Float32, reflect.Float64:
return a.Float() < b.Float()
case reflect.String:
return a.String() < b.String()
case reflect.Uintptr:
return a.Uint() < b.Uint()
case reflect.Array:
// Compare the contents of both arrays.
l := a.Len()
for i := 0; i < l; i++ {
av := a.Index(i)
bv := b.Index(i)
if av.Interface() == bv.Interface() {
continue
}
return valueSortLess(av, bv)
}
}
return a.String() < b.String()
}
// Less returns whether the value at index i should sort before the
// value at index j. It is part of the sort.Interface implementation.
func (s *valuesSorter) Less(i, j int) bool {
if s.strings == nil {
return valueSortLess(s.values[i], s.values[j])
}
return s.strings[i] < s.strings[j]
}
// sortValues is a sort function that handles both native types and any type that
// can be converted to error or Stringer. Other inputs are sorted according to
// their Value.String() value to ensure display stability.
func sortValues(values []reflect.Value, cs *ConfigState) {
if len(values) == 0 {
return
}
sort.Sort(newValuesSorter(values, cs))
}

View File

@ -0,0 +1,298 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew_test
import (
"fmt"
"reflect"
"testing"
"github.com/davecgh/go-spew/spew"
)
// custom type to test Stinger interface on non-pointer receiver.
type stringer string
// String implements the Stringer interface for testing invocation of custom
// stringers on types with non-pointer receivers.
func (s stringer) String() string {
return "stringer " + string(s)
}
// custom type to test Stinger interface on pointer receiver.
type pstringer string
// String implements the Stringer interface for testing invocation of custom
// stringers on types with only pointer receivers.
func (s *pstringer) String() string {
return "stringer " + string(*s)
}
// xref1 and xref2 are cross referencing structs for testing circular reference
// detection.
type xref1 struct {
ps2 *xref2
}
type xref2 struct {
ps1 *xref1
}
// indirCir1, indirCir2, and indirCir3 are used to generate an indirect circular
// reference for testing detection.
type indirCir1 struct {
ps2 *indirCir2
}
type indirCir2 struct {
ps3 *indirCir3
}
type indirCir3 struct {
ps1 *indirCir1
}
// embed is used to test embedded structures.
type embed struct {
a string
}
// embedwrap is used to test embedded structures.
type embedwrap struct {
*embed
e *embed
}
// panicer is used to intentionally cause a panic for testing spew properly
// handles them
type panicer int
func (p panicer) String() string {
panic("test panic")
}
// customError is used to test custom error interface invocation.
type customError int
func (e customError) Error() string {
return fmt.Sprintf("error: %d", int(e))
}
// stringizeWants converts a slice of wanted test output into a format suitable
// for a test error message.
func stringizeWants(wants []string) string {
s := ""
for i, want := range wants {
if i > 0 {
s += fmt.Sprintf("want%d: %s", i+1, want)
} else {
s += "want: " + want
}
}
return s
}
// testFailed returns whether or not a test failed by checking if the result
// of the test is in the slice of wanted strings.
func testFailed(result string, wants []string) bool {
for _, want := range wants {
if result == want {
return false
}
}
return true
}
type sortableStruct struct {
x int
}
func (ss sortableStruct) String() string {
return fmt.Sprintf("ss.%d", ss.x)
}
type unsortableStruct struct {
x int
}
type sortTestCase struct {
input []reflect.Value
expected []reflect.Value
}
func helpTestSortValues(tests []sortTestCase, cs *spew.ConfigState, t *testing.T) {
getInterfaces := func(values []reflect.Value) []interface{} {
interfaces := []interface{}{}
for _, v := range values {
interfaces = append(interfaces, v.Interface())
}
return interfaces
}
for _, test := range tests {
spew.SortValues(test.input, cs)
// reflect.DeepEqual cannot really make sense of reflect.Value,
// probably because of all the pointer tricks. For instance,
// v(2.0) != v(2.0) on a 32-bits system. Turn them into interface{}
// instead.
input := getInterfaces(test.input)
expected := getInterfaces(test.expected)
if !reflect.DeepEqual(input, expected) {
t.Errorf("Sort mismatch:\n %v != %v", input, expected)
}
}
}
// TestSortValues ensures the sort functionality for relect.Value based sorting
// works as intended.
func TestSortValues(t *testing.T) {
v := reflect.ValueOf
a := v("a")
b := v("b")
c := v("c")
embedA := v(embed{"a"})
embedB := v(embed{"b"})
embedC := v(embed{"c"})
tests := []sortTestCase{
// No values.
{
[]reflect.Value{},
[]reflect.Value{},
},
// Bools.
{
[]reflect.Value{v(false), v(true), v(false)},
[]reflect.Value{v(false), v(false), v(true)},
},
// Ints.
{
[]reflect.Value{v(2), v(1), v(3)},
[]reflect.Value{v(1), v(2), v(3)},
},
// Uints.
{
[]reflect.Value{v(uint8(2)), v(uint8(1)), v(uint8(3))},
[]reflect.Value{v(uint8(1)), v(uint8(2)), v(uint8(3))},
},
// Floats.
{
[]reflect.Value{v(2.0), v(1.0), v(3.0)},
[]reflect.Value{v(1.0), v(2.0), v(3.0)},
},
// Strings.
{
[]reflect.Value{b, a, c},
[]reflect.Value{a, b, c},
},
// Array
{
[]reflect.Value{v([3]int{3, 2, 1}), v([3]int{1, 3, 2}), v([3]int{1, 2, 3})},
[]reflect.Value{v([3]int{1, 2, 3}), v([3]int{1, 3, 2}), v([3]int{3, 2, 1})},
},
// Uintptrs.
{
[]reflect.Value{v(uintptr(2)), v(uintptr(1)), v(uintptr(3))},
[]reflect.Value{v(uintptr(1)), v(uintptr(2)), v(uintptr(3))},
},
// SortableStructs.
{
// Note: not sorted - DisableMethods is set.
[]reflect.Value{v(sortableStruct{2}), v(sortableStruct{1}), v(sortableStruct{3})},
[]reflect.Value{v(sortableStruct{2}), v(sortableStruct{1}), v(sortableStruct{3})},
},
// UnsortableStructs.
{
// Note: not sorted - SpewKeys is false.
[]reflect.Value{v(unsortableStruct{2}), v(unsortableStruct{1}), v(unsortableStruct{3})},
[]reflect.Value{v(unsortableStruct{2}), v(unsortableStruct{1}), v(unsortableStruct{3})},
},
// Invalid.
{
[]reflect.Value{embedB, embedA, embedC},
[]reflect.Value{embedB, embedA, embedC},
},
}
cs := spew.ConfigState{DisableMethods: true, SpewKeys: false}
helpTestSortValues(tests, &cs, t)
}
// TestSortValuesWithMethods ensures the sort functionality for relect.Value
// based sorting works as intended when using string methods.
func TestSortValuesWithMethods(t *testing.T) {
v := reflect.ValueOf
a := v("a")
b := v("b")
c := v("c")
tests := []sortTestCase{
// Ints.
{
[]reflect.Value{v(2), v(1), v(3)},
[]reflect.Value{v(1), v(2), v(3)},
},
// Strings.
{
[]reflect.Value{b, a, c},
[]reflect.Value{a, b, c},
},
// SortableStructs.
{
[]reflect.Value{v(sortableStruct{2}), v(sortableStruct{1}), v(sortableStruct{3})},
[]reflect.Value{v(sortableStruct{1}), v(sortableStruct{2}), v(sortableStruct{3})},
},
// UnsortableStructs.
{
// Note: not sorted - SpewKeys is false.
[]reflect.Value{v(unsortableStruct{2}), v(unsortableStruct{1}), v(unsortableStruct{3})},
[]reflect.Value{v(unsortableStruct{2}), v(unsortableStruct{1}), v(unsortableStruct{3})},
},
}
cs := spew.ConfigState{DisableMethods: false, SpewKeys: false}
helpTestSortValues(tests, &cs, t)
}
// TestSortValuesWithSpew ensures the sort functionality for relect.Value
// based sorting works as intended when using spew to stringify keys.
func TestSortValuesWithSpew(t *testing.T) {
v := reflect.ValueOf
a := v("a")
b := v("b")
c := v("c")
tests := []sortTestCase{
// Ints.
{
[]reflect.Value{v(2), v(1), v(3)},
[]reflect.Value{v(1), v(2), v(3)},
},
// Strings.
{
[]reflect.Value{b, a, c},
[]reflect.Value{a, b, c},
},
// SortableStructs.
{
[]reflect.Value{v(sortableStruct{2}), v(sortableStruct{1}), v(sortableStruct{3})},
[]reflect.Value{v(sortableStruct{1}), v(sortableStruct{2}), v(sortableStruct{3})},
},
// UnsortableStructs.
{
[]reflect.Value{v(unsortableStruct{2}), v(unsortableStruct{1}), v(unsortableStruct{3})},
[]reflect.Value{v(unsortableStruct{1}), v(unsortableStruct{2}), v(unsortableStruct{3})},
},
}
cs := spew.ConfigState{DisableMethods: true, SpewKeys: true}
helpTestSortValues(tests, &cs, t)
}

View File

@ -0,0 +1,294 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew
import (
"bytes"
"fmt"
"io"
"os"
)
// ConfigState houses the configuration options used by spew to format and
// display values. There is a global instance, Config, that is used to control
// all top-level Formatter and Dump functionality. Each ConfigState instance
// provides methods equivalent to the top-level functions.
//
// The zero value for ConfigState provides no indentation. You would typically
// want to set it to a space or a tab.
//
// Alternatively, you can use NewDefaultConfig to get a ConfigState instance
// with default settings. See the documentation of NewDefaultConfig for default
// values.
type ConfigState struct {
// Indent specifies the string to use for each indentation level. The
// global config instance that all top-level functions use set this to a
// single space by default. If you would like more indentation, you might
// set this to a tab with "\t" or perhaps two spaces with " ".
Indent string
// MaxDepth controls the maximum number of levels to descend into nested
// data structures. The default, 0, means there is no limit.
//
// NOTE: Circular data structures are properly detected, so it is not
// necessary to set this value unless you specifically want to limit deeply
// nested data structures.
MaxDepth int
// DisableMethods specifies whether or not error and Stringer interfaces are
// invoked for types that implement them.
DisableMethods bool
// DisablePointerMethods specifies whether or not to check for and invoke
// error and Stringer interfaces on types which only accept a pointer
// receiver when the current type is not a pointer.
//
// NOTE: This might be an unsafe action since calling one of these methods
// with a pointer receiver could technically mutate the value, however,
// in practice, types which choose to satisify an error or Stringer
// interface with a pointer receiver should not be mutating their state
// inside these interface methods.
DisablePointerMethods bool
// ContinueOnMethod specifies whether or not recursion should continue once
// a custom error or Stringer interface is invoked. The default, false,
// means it will print the results of invoking the custom error or Stringer
// interface and return immediately instead of continuing to recurse into
// the internals of the data type.
//
// NOTE: This flag does not have any effect if method invocation is disabled
// via the DisableMethods or DisablePointerMethods options.
ContinueOnMethod bool
// SortKeys specifies map keys should be sorted before being printed. Use
// this to have a more deterministic, diffable output. Note that only
// native types (bool, int, uint, floats, uintptr and string) and types
// that support the error or Stringer interfaces (if methods are
// enabled) are supported, with other types sorted according to the
// reflect.Value.String() output which guarantees display stability.
SortKeys bool
// SpewKeys specifies that, as a last resort attempt, map keys should
// be spewed to strings and sorted by those strings. This is only
// considered if SortKeys is true.
SpewKeys bool
}
// Config is the active configuration of the top-level functions.
// The configuration can be changed by modifying the contents of spew.Config.
var Config = ConfigState{Indent: " "}
// Errorf is a wrapper for fmt.Errorf that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the formatted string as a value that satisfies error. See NewFormatter
// for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Errorf(format, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Errorf(format string, a ...interface{}) (err error) {
return fmt.Errorf(format, c.convertArgs(a)...)
}
// Fprint is a wrapper for fmt.Fprint that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprint(w, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Fprint(w io.Writer, a ...interface{}) (n int, err error) {
return fmt.Fprint(w, c.convertArgs(a)...)
}
// Fprintf is a wrapper for fmt.Fprintf that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprintf(w, format, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Fprintf(w io.Writer, format string, a ...interface{}) (n int, err error) {
return fmt.Fprintf(w, format, c.convertArgs(a)...)
}
// Fprintln is a wrapper for fmt.Fprintln that treats each argument as if it
// passed with a Formatter interface returned by c.NewFormatter. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprintln(w, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Fprintln(w io.Writer, a ...interface{}) (n int, err error) {
return fmt.Fprintln(w, c.convertArgs(a)...)
}
// Print is a wrapper for fmt.Print that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Print(c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Print(a ...interface{}) (n int, err error) {
return fmt.Print(c.convertArgs(a)...)
}
// Printf is a wrapper for fmt.Printf that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Printf(format, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Printf(format string, a ...interface{}) (n int, err error) {
return fmt.Printf(format, c.convertArgs(a)...)
}
// Println is a wrapper for fmt.Println that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Println(c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Println(a ...interface{}) (n int, err error) {
return fmt.Println(c.convertArgs(a)...)
}
// Sprint is a wrapper for fmt.Sprint that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprint(c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Sprint(a ...interface{}) string {
return fmt.Sprint(c.convertArgs(a)...)
}
// Sprintf is a wrapper for fmt.Sprintf that treats each argument as if it were
// passed with a Formatter interface returned by c.NewFormatter. It returns
// the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprintf(format, c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Sprintf(format string, a ...interface{}) string {
return fmt.Sprintf(format, c.convertArgs(a)...)
}
// Sprintln is a wrapper for fmt.Sprintln that treats each argument as if it
// were passed with a Formatter interface returned by c.NewFormatter. It
// returns the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprintln(c.NewFormatter(a), c.NewFormatter(b))
func (c *ConfigState) Sprintln(a ...interface{}) string {
return fmt.Sprintln(c.convertArgs(a)...)
}
/*
NewFormatter returns a custom formatter that satisfies the fmt.Formatter
interface. As a result, it integrates cleanly with standard fmt package
printing functions. The formatter is useful for inline printing of smaller data
types similar to the standard %v format specifier.
The custom formatter only responds to the %v (most compact), %+v (adds pointer
addresses), %#v (adds types), and %#+v (adds types and pointer addresses) verb
combinations. Any other verbs such as %x and %q will be sent to the the
standard fmt package for formatting. In addition, the custom formatter ignores
the width and precision arguments (however they will still work on the format
specifiers not handled by the custom formatter).
Typically this function shouldn't be called directly. It is much easier to make
use of the custom formatter by calling one of the convenience functions such as
c.Printf, c.Println, or c.Printf.
*/
func (c *ConfigState) NewFormatter(v interface{}) fmt.Formatter {
return newFormatter(c, v)
}
// Fdump formats and displays the passed arguments to io.Writer w. It formats
// exactly the same as Dump.
func (c *ConfigState) Fdump(w io.Writer, a ...interface{}) {
fdump(c, w, a...)
}
/*
Dump displays the passed parameters to standard out with newlines, customizable
indentation, and additional debug information such as complete types and all
pointer addresses used to indirect to the final value. It provides the
following features over the built-in printing facilities provided by the fmt
package:
* Pointers are dereferenced and followed
* Circular data structures are detected and handled properly
* Custom Stringer/error interfaces are optionally invoked, including
on unexported types
* Custom types which only implement the Stringer/error interfaces via
a pointer receiver are optionally invoked when passing non-pointer
variables
* Byte arrays and slices are dumped like the hexdump -C command which
includes offsets, byte values in hex, and ASCII output
The configuration options are controlled by modifying the public members
of c. See ConfigState for options documentation.
See Fdump if you would prefer dumping to an arbitrary io.Writer or Sdump to
get the formatted result as a string.
*/
func (c *ConfigState) Dump(a ...interface{}) {
fdump(c, os.Stdout, a...)
}
// Sdump returns a string with the passed arguments formatted exactly the same
// as Dump.
func (c *ConfigState) Sdump(a ...interface{}) string {
var buf bytes.Buffer
fdump(c, &buf, a...)
return buf.String()
}
// convertArgs accepts a slice of arguments and returns a slice of the same
// length with each argument converted to a spew Formatter interface using
// the ConfigState associated with s.
func (c *ConfigState) convertArgs(args []interface{}) (formatters []interface{}) {
formatters = make([]interface{}, len(args))
for index, arg := range args {
formatters[index] = newFormatter(c, arg)
}
return formatters
}
// NewDefaultConfig returns a ConfigState with the following default settings.
//
// Indent: " "
// MaxDepth: 0
// DisableMethods: false
// DisablePointerMethods: false
// ContinueOnMethod: false
// SortKeys: false
func NewDefaultConfig() *ConfigState {
return &ConfigState{Indent: " "}
}

View File

@ -0,0 +1,202 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
/*
Package spew implements a deep pretty printer for Go data structures to aid in
debugging.
A quick overview of the additional features spew provides over the built-in
printing facilities for Go data types are as follows:
* Pointers are dereferenced and followed
* Circular data structures are detected and handled properly
* Custom Stringer/error interfaces are optionally invoked, including
on unexported types
* Custom types which only implement the Stringer/error interfaces via
a pointer receiver are optionally invoked when passing non-pointer
variables
* Byte arrays and slices are dumped like the hexdump -C command which
includes offsets, byte values in hex, and ASCII output (only when using
Dump style)
There are two different approaches spew allows for dumping Go data structures:
* Dump style which prints with newlines, customizable indentation,
and additional debug information such as types and all pointer addresses
used to indirect to the final value
* A custom Formatter interface that integrates cleanly with the standard fmt
package and replaces %v, %+v, %#v, and %#+v to provide inline printing
similar to the default %v while providing the additional functionality
outlined above and passing unsupported format verbs such as %x and %q
along to fmt
Quick Start
This section demonstrates how to quickly get started with spew. See the
sections below for further details on formatting and configuration options.
To dump a variable with full newlines, indentation, type, and pointer
information use Dump, Fdump, or Sdump:
spew.Dump(myVar1, myVar2, ...)
spew.Fdump(someWriter, myVar1, myVar2, ...)
str := spew.Sdump(myVar1, myVar2, ...)
Alternatively, if you would prefer to use format strings with a compacted inline
printing style, use the convenience wrappers Printf, Fprintf, etc with
%v (most compact), %+v (adds pointer addresses), %#v (adds types), or
%#+v (adds types and pointer addresses):
spew.Printf("myVar1: %v -- myVar2: %+v", myVar1, myVar2)
spew.Printf("myVar3: %#v -- myVar4: %#+v", myVar3, myVar4)
spew.Fprintf(someWriter, "myVar1: %v -- myVar2: %+v", myVar1, myVar2)
spew.Fprintf(someWriter, "myVar3: %#v -- myVar4: %#+v", myVar3, myVar4)
Configuration Options
Configuration of spew is handled by fields in the ConfigState type. For
convenience, all of the top-level functions use a global state available
via the spew.Config global.
It is also possible to create a ConfigState instance that provides methods
equivalent to the top-level functions. This allows concurrent configuration
options. See the ConfigState documentation for more details.
The following configuration options are available:
* Indent
String to use for each indentation level for Dump functions.
It is a single space by default. A popular alternative is "\t".
* MaxDepth
Maximum number of levels to descend into nested data structures.
There is no limit by default.
* DisableMethods
Disables invocation of error and Stringer interface methods.
Method invocation is enabled by default.
* DisablePointerMethods
Disables invocation of error and Stringer interface methods on types
which only accept pointer receivers from non-pointer variables.
Pointer method invocation is enabled by default.
* ContinueOnMethod
Enables recursion into types after invoking error and Stringer interface
methods. Recursion after method invocation is disabled by default.
* SortKeys
Specifies map keys should be sorted before being printed. Use
this to have a more deterministic, diffable output. Note that
only native types (bool, int, uint, floats, uintptr and string)
and types which implement error or Stringer interfaces are
supported with other types sorted according to the
reflect.Value.String() output which guarantees display
stability. Natural map order is used by default.
* SpewKeys
Specifies that, as a last resort attempt, map keys should be
spewed to strings and sorted by those strings. This is only
considered if SortKeys is true.
Dump Usage
Simply call spew.Dump with a list of variables you want to dump:
spew.Dump(myVar1, myVar2, ...)
You may also call spew.Fdump if you would prefer to output to an arbitrary
io.Writer. For example, to dump to standard error:
spew.Fdump(os.Stderr, myVar1, myVar2, ...)
A third option is to call spew.Sdump to get the formatted output as a string:
str := spew.Sdump(myVar1, myVar2, ...)
Sample Dump Output
See the Dump example for details on the setup of the types and variables being
shown here.
(main.Foo) {
unexportedField: (*main.Bar)(0xf84002e210)({
flag: (main.Flag) flagTwo,
data: (uintptr) <nil>
}),
ExportedField: (map[interface {}]interface {}) (len=1) {
(string) (len=3) "one": (bool) true
}
}
Byte (and uint8) arrays and slices are displayed uniquely like the hexdump -C
command as shown.
([]uint8) (len=32 cap=32) {
00000000 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f 20 |............... |
00000010 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f 30 |!"#$%&'()*+,-./0|
00000020 31 32 |12|
}
Custom Formatter
Spew provides a custom formatter that implements the fmt.Formatter interface
so that it integrates cleanly with standard fmt package printing functions. The
formatter is useful for inline printing of smaller data types similar to the
standard %v format specifier.
The custom formatter only responds to the %v (most compact), %+v (adds pointer
addresses), %#v (adds types), or %#+v (adds types and pointer addresses) verb
combinations. Any other verbs such as %x and %q will be sent to the the
standard fmt package for formatting. In addition, the custom formatter ignores
the width and precision arguments (however they will still work on the format
specifiers not handled by the custom formatter).
Custom Formatter Usage
The simplest way to make use of the spew custom formatter is to call one of the
convenience functions such as spew.Printf, spew.Println, or spew.Printf. The
functions have syntax you are most likely already familiar with:
spew.Printf("myVar1: %v -- myVar2: %+v", myVar1, myVar2)
spew.Printf("myVar3: %#v -- myVar4: %#+v", myVar3, myVar4)
spew.Println(myVar, myVar2)
spew.Fprintf(os.Stderr, "myVar1: %v -- myVar2: %+v", myVar1, myVar2)
spew.Fprintf(os.Stderr, "myVar3: %#v -- myVar4: %#+v", myVar3, myVar4)
See the Index for the full list convenience functions.
Sample Formatter Output
Double pointer to a uint8:
%v: <**>5
%+v: <**>(0xf8400420d0->0xf8400420c8)5
%#v: (**uint8)5
%#+v: (**uint8)(0xf8400420d0->0xf8400420c8)5
Pointer to circular struct with a uint8 field and a pointer to itself:
%v: <*>{1 <*><shown>}
%+v: <*>(0xf84003e260){ui8:1 c:<*>(0xf84003e260)<shown>}
%#v: (*main.circular){ui8:(uint8)1 c:(*main.circular)<shown>}
%#+v: (*main.circular)(0xf84003e260){ui8:(uint8)1 c:(*main.circular)(0xf84003e260)<shown>}
See the Printf example for details on the setup of variables being shown
here.
Errors
Since it is possible for custom Stringer/error interfaces to panic, spew
detects them and handles them internally by printing the panic information
inline with the output. Since spew is intended to provide deep pretty printing
capabilities on structures, it intentionally does not return any errors.
*/
package spew

View File

@ -0,0 +1,506 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew
import (
"bytes"
"encoding/hex"
"fmt"
"io"
"os"
"reflect"
"regexp"
"strconv"
"strings"
)
var (
// uint8Type is a reflect.Type representing a uint8. It is used to
// convert cgo types to uint8 slices for hexdumping.
uint8Type = reflect.TypeOf(uint8(0))
// cCharRE is a regular expression that matches a cgo char.
// It is used to detect character arrays to hexdump them.
cCharRE = regexp.MustCompile("^.*\\._Ctype_char$")
// cUnsignedCharRE is a regular expression that matches a cgo unsigned
// char. It is used to detect unsigned character arrays to hexdump
// them.
cUnsignedCharRE = regexp.MustCompile("^.*\\._Ctype_unsignedchar$")
// cUint8tCharRE is a regular expression that matches a cgo uint8_t.
// It is used to detect uint8_t arrays to hexdump them.
cUint8tCharRE = regexp.MustCompile("^.*\\._Ctype_uint8_t$")
)
// dumpState contains information about the state of a dump operation.
type dumpState struct {
w io.Writer
depth int
pointers map[uintptr]int
ignoreNextType bool
ignoreNextIndent bool
cs *ConfigState
}
// indent performs indentation according to the depth level and cs.Indent
// option.
func (d *dumpState) indent() {
if d.ignoreNextIndent {
d.ignoreNextIndent = false
return
}
d.w.Write(bytes.Repeat([]byte(d.cs.Indent), d.depth))
}
// unpackValue returns values inside of non-nil interfaces when possible.
// This is useful for data types like structs, arrays, slices, and maps which
// can contain varying types packed inside an interface.
func (d *dumpState) unpackValue(v reflect.Value) reflect.Value {
if v.Kind() == reflect.Interface && !v.IsNil() {
v = v.Elem()
}
return v
}
// dumpPtr handles formatting of pointers by indirecting them as necessary.
func (d *dumpState) dumpPtr(v reflect.Value) {
// Remove pointers at or below the current depth from map used to detect
// circular refs.
for k, depth := range d.pointers {
if depth >= d.depth {
delete(d.pointers, k)
}
}
// Keep list of all dereferenced pointers to show later.
pointerChain := make([]uintptr, 0)
// Figure out how many levels of indirection there are by dereferencing
// pointers and unpacking interfaces down the chain while detecting circular
// references.
nilFound := false
cycleFound := false
indirects := 0
ve := v
for ve.Kind() == reflect.Ptr {
if ve.IsNil() {
nilFound = true
break
}
indirects++
addr := ve.Pointer()
pointerChain = append(pointerChain, addr)
if pd, ok := d.pointers[addr]; ok && pd < d.depth {
cycleFound = true
indirects--
break
}
d.pointers[addr] = d.depth
ve = ve.Elem()
if ve.Kind() == reflect.Interface {
if ve.IsNil() {
nilFound = true
break
}
ve = ve.Elem()
}
}
// Display type information.
d.w.Write(openParenBytes)
d.w.Write(bytes.Repeat(asteriskBytes, indirects))
d.w.Write([]byte(ve.Type().String()))
d.w.Write(closeParenBytes)
// Display pointer information.
if len(pointerChain) > 0 {
d.w.Write(openParenBytes)
for i, addr := range pointerChain {
if i > 0 {
d.w.Write(pointerChainBytes)
}
printHexPtr(d.w, addr)
}
d.w.Write(closeParenBytes)
}
// Display dereferenced value.
d.w.Write(openParenBytes)
switch {
case nilFound == true:
d.w.Write(nilAngleBytes)
case cycleFound == true:
d.w.Write(circularBytes)
default:
d.ignoreNextType = true
d.dump(ve)
}
d.w.Write(closeParenBytes)
}
// dumpSlice handles formatting of arrays and slices. Byte (uint8 under
// reflection) arrays and slices are dumped in hexdump -C fashion.
func (d *dumpState) dumpSlice(v reflect.Value) {
// Determine whether this type should be hex dumped or not. Also,
// for types which should be hexdumped, try to use the underlying data
// first, then fall back to trying to convert them to a uint8 slice.
var buf []uint8
doConvert := false
doHexDump := false
numEntries := v.Len()
if numEntries > 0 {
vt := v.Index(0).Type()
vts := vt.String()
switch {
// C types that need to be converted.
case cCharRE.MatchString(vts):
fallthrough
case cUnsignedCharRE.MatchString(vts):
fallthrough
case cUint8tCharRE.MatchString(vts):
doConvert = true
// Try to use existing uint8 slices and fall back to converting
// and copying if that fails.
case vt.Kind() == reflect.Uint8:
// We need an addressable interface to convert the type back
// into a byte slice. However, the reflect package won't give
// us an interface on certain things like unexported struct
// fields in order to enforce visibility rules. We use unsafe
// to bypass these restrictions since this package does not
// mutate the values.
vs := v
if !vs.CanInterface() || !vs.CanAddr() {
vs = unsafeReflectValue(vs)
}
vs = vs.Slice(0, numEntries)
// Use the existing uint8 slice if it can be type
// asserted.
iface := vs.Interface()
if slice, ok := iface.([]uint8); ok {
buf = slice
doHexDump = true
break
}
// The underlying data needs to be converted if it can't
// be type asserted to a uint8 slice.
doConvert = true
}
// Copy and convert the underlying type if needed.
if doConvert && vt.ConvertibleTo(uint8Type) {
// Convert and copy each element into a uint8 byte
// slice.
buf = make([]uint8, numEntries)
for i := 0; i < numEntries; i++ {
vv := v.Index(i)
buf[i] = uint8(vv.Convert(uint8Type).Uint())
}
doHexDump = true
}
}
// Hexdump the entire slice as needed.
if doHexDump {
indent := strings.Repeat(d.cs.Indent, d.depth)
str := indent + hex.Dump(buf)
str = strings.Replace(str, "\n", "\n"+indent, -1)
str = strings.TrimRight(str, d.cs.Indent)
d.w.Write([]byte(str))
return
}
// Recursively call dump for each item.
for i := 0; i < numEntries; i++ {
d.dump(d.unpackValue(v.Index(i)))
if i < (numEntries - 1) {
d.w.Write(commaNewlineBytes)
} else {
d.w.Write(newlineBytes)
}
}
}
// dump is the main workhorse for dumping a value. It uses the passed reflect
// value to figure out what kind of object we are dealing with and formats it
// appropriately. It is a recursive function, however circular data structures
// are detected and handled properly.
func (d *dumpState) dump(v reflect.Value) {
// Handle invalid reflect values immediately.
kind := v.Kind()
if kind == reflect.Invalid {
d.w.Write(invalidAngleBytes)
return
}
// Handle pointers specially.
if kind == reflect.Ptr {
d.indent()
d.dumpPtr(v)
return
}
// Print type information unless already handled elsewhere.
if !d.ignoreNextType {
d.indent()
d.w.Write(openParenBytes)
d.w.Write([]byte(v.Type().String()))
d.w.Write(closeParenBytes)
d.w.Write(spaceBytes)
}
d.ignoreNextType = false
// Display length and capacity if the built-in len and cap functions
// work with the value's kind and the len/cap itself is non-zero.
valueLen, valueCap := 0, 0
switch v.Kind() {
case reflect.Array, reflect.Slice, reflect.Chan:
valueLen, valueCap = v.Len(), v.Cap()
case reflect.Map, reflect.String:
valueLen = v.Len()
}
if valueLen != 0 || valueCap != 0 {
d.w.Write(openParenBytes)
if valueLen != 0 {
d.w.Write(lenEqualsBytes)
printInt(d.w, int64(valueLen), 10)
}
if valueCap != 0 {
if valueLen != 0 {
d.w.Write(spaceBytes)
}
d.w.Write(capEqualsBytes)
printInt(d.w, int64(valueCap), 10)
}
d.w.Write(closeParenBytes)
d.w.Write(spaceBytes)
}
// Call Stringer/error interfaces if they exist and the handle methods flag
// is enabled
if !d.cs.DisableMethods {
if (kind != reflect.Invalid) && (kind != reflect.Interface) {
if handled := handleMethods(d.cs, d.w, v); handled {
return
}
}
}
switch kind {
case reflect.Invalid:
// Do nothing. We should never get here since invalid has already
// been handled above.
case reflect.Bool:
printBool(d.w, v.Bool())
case reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64, reflect.Int:
printInt(d.w, v.Int(), 10)
case reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uint:
printUint(d.w, v.Uint(), 10)
case reflect.Float32:
printFloat(d.w, v.Float(), 32)
case reflect.Float64:
printFloat(d.w, v.Float(), 64)
case reflect.Complex64:
printComplex(d.w, v.Complex(), 32)
case reflect.Complex128:
printComplex(d.w, v.Complex(), 64)
case reflect.Slice:
if v.IsNil() {
d.w.Write(nilAngleBytes)
break
}
fallthrough
case reflect.Array:
d.w.Write(openBraceNewlineBytes)
d.depth++
if (d.cs.MaxDepth != 0) && (d.depth > d.cs.MaxDepth) {
d.indent()
d.w.Write(maxNewlineBytes)
} else {
d.dumpSlice(v)
}
d.depth--
d.indent()
d.w.Write(closeBraceBytes)
case reflect.String:
d.w.Write([]byte(strconv.Quote(v.String())))
case reflect.Interface:
// The only time we should get here is for nil interfaces due to
// unpackValue calls.
if v.IsNil() {
d.w.Write(nilAngleBytes)
}
case reflect.Ptr:
// Do nothing. We should never get here since pointers have already
// been handled above.
case reflect.Map:
// nil maps should be indicated as different than empty maps
if v.IsNil() {
d.w.Write(nilAngleBytes)
break
}
d.w.Write(openBraceNewlineBytes)
d.depth++
if (d.cs.MaxDepth != 0) && (d.depth > d.cs.MaxDepth) {
d.indent()
d.w.Write(maxNewlineBytes)
} else {
numEntries := v.Len()
keys := v.MapKeys()
if d.cs.SortKeys {
sortValues(keys, d.cs)
}
for i, key := range keys {
d.dump(d.unpackValue(key))
d.w.Write(colonSpaceBytes)
d.ignoreNextIndent = true
d.dump(d.unpackValue(v.MapIndex(key)))
if i < (numEntries - 1) {
d.w.Write(commaNewlineBytes)
} else {
d.w.Write(newlineBytes)
}
}
}
d.depth--
d.indent()
d.w.Write(closeBraceBytes)
case reflect.Struct:
d.w.Write(openBraceNewlineBytes)
d.depth++
if (d.cs.MaxDepth != 0) && (d.depth > d.cs.MaxDepth) {
d.indent()
d.w.Write(maxNewlineBytes)
} else {
vt := v.Type()
numFields := v.NumField()
for i := 0; i < numFields; i++ {
d.indent()
vtf := vt.Field(i)
d.w.Write([]byte(vtf.Name))
d.w.Write(colonSpaceBytes)
d.ignoreNextIndent = true
d.dump(d.unpackValue(v.Field(i)))
if i < (numFields - 1) {
d.w.Write(commaNewlineBytes)
} else {
d.w.Write(newlineBytes)
}
}
}
d.depth--
d.indent()
d.w.Write(closeBraceBytes)
case reflect.Uintptr:
printHexPtr(d.w, uintptr(v.Uint()))
case reflect.UnsafePointer, reflect.Chan, reflect.Func:
printHexPtr(d.w, v.Pointer())
// There were not any other types at the time this code was written, but
// fall back to letting the default fmt package handle it in case any new
// types are added.
default:
if v.CanInterface() {
fmt.Fprintf(d.w, "%v", v.Interface())
} else {
fmt.Fprintf(d.w, "%v", v.String())
}
}
}
// fdump is a helper function to consolidate the logic from the various public
// methods which take varying writers and config states.
func fdump(cs *ConfigState, w io.Writer, a ...interface{}) {
for _, arg := range a {
if arg == nil {
w.Write(interfaceBytes)
w.Write(spaceBytes)
w.Write(nilAngleBytes)
w.Write(newlineBytes)
continue
}
d := dumpState{w: w, cs: cs}
d.pointers = make(map[uintptr]int)
d.dump(reflect.ValueOf(arg))
d.w.Write(newlineBytes)
}
}
// Fdump formats and displays the passed arguments to io.Writer w. It formats
// exactly the same as Dump.
func Fdump(w io.Writer, a ...interface{}) {
fdump(&Config, w, a...)
}
// Sdump returns a string with the passed arguments formatted exactly the same
// as Dump.
func Sdump(a ...interface{}) string {
var buf bytes.Buffer
fdump(&Config, &buf, a...)
return buf.String()
}
/*
Dump displays the passed parameters to standard out with newlines, customizable
indentation, and additional debug information such as complete types and all
pointer addresses used to indirect to the final value. It provides the
following features over the built-in printing facilities provided by the fmt
package:
* Pointers are dereferenced and followed
* Circular data structures are detected and handled properly
* Custom Stringer/error interfaces are optionally invoked, including
on unexported types
* Custom types which only implement the Stringer/error interfaces via
a pointer receiver are optionally invoked when passing non-pointer
variables
* Byte arrays and slices are dumped like the hexdump -C command which
includes offsets, byte values in hex, and ASCII output
The configuration options are controlled by an exported package global,
spew.Config. See ConfigState for options documentation.
See Fdump if you would prefer dumping to an arbitrary io.Writer or Sdump to
get the formatted result as a string.
*/
func Dump(a ...interface{}) {
fdump(&Config, os.Stdout, a...)
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,97 @@
// Copyright (c) 2013 Dave Collins <dave@davec.name>
//
// Permission to use, copy, modify, and distribute this software for any
// purpose with or without fee is hereby granted, provided that the above
// copyright notice and this permission notice appear in all copies.
//
// THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
// WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
// MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
// ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
// WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
// ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
// OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
// NOTE: Due to the following build constraints, this file will only be compiled
// when both cgo is supported and "-tags testcgo" is added to the go test
// command line. This means the cgo tests are only added (and hence run) when
// specifially requested. This configuration is used because spew itself
// does not require cgo to run even though it does handle certain cgo types
// specially. Rather than forcing all clients to require cgo and an external
// C compiler just to run the tests, this scheme makes them optional.
// +build cgo,testcgo
package spew_test
import (
"fmt"
"github.com/davecgh/go-spew/spew/testdata"
)
func addCgoDumpTests() {
// C char pointer.
v := testdata.GetCgoCharPointer()
nv := testdata.GetCgoNullCharPointer()
pv := &v
vcAddr := fmt.Sprintf("%p", v)
vAddr := fmt.Sprintf("%p", pv)
pvAddr := fmt.Sprintf("%p", &pv)
vt := "*testdata._Ctype_char"
vs := "116"
addDumpTest(v, "("+vt+")("+vcAddr+")("+vs+")\n")
addDumpTest(pv, "(*"+vt+")("+vAddr+"->"+vcAddr+")("+vs+")\n")
addDumpTest(&pv, "(**"+vt+")("+pvAddr+"->"+vAddr+"->"+vcAddr+")("+vs+")\n")
addDumpTest(nv, "("+vt+")(<nil>)\n")
// C char array.
v2, v2l, v2c := testdata.GetCgoCharArray()
v2Len := fmt.Sprintf("%d", v2l)
v2Cap := fmt.Sprintf("%d", v2c)
v2t := "[6]testdata._Ctype_char"
v2s := "(len=" + v2Len + " cap=" + v2Cap + ") " +
"{\n 00000000 74 65 73 74 32 00 " +
" |test2.|\n}"
addDumpTest(v2, "("+v2t+") "+v2s+"\n")
// C unsigned char array.
v3, v3l, v3c := testdata.GetCgoUnsignedCharArray()
v3Len := fmt.Sprintf("%d", v3l)
v3Cap := fmt.Sprintf("%d", v3c)
v3t := "[6]testdata._Ctype_unsignedchar"
v3s := "(len=" + v3Len + " cap=" + v3Cap + ") " +
"{\n 00000000 74 65 73 74 33 00 " +
" |test3.|\n}"
addDumpTest(v3, "("+v3t+") "+v3s+"\n")
// C signed char array.
v4, v4l, v4c := testdata.GetCgoSignedCharArray()
v4Len := fmt.Sprintf("%d", v4l)
v4Cap := fmt.Sprintf("%d", v4c)
v4t := "[6]testdata._Ctype_schar"
v4t2 := "testdata._Ctype_schar"
v4s := "(len=" + v4Len + " cap=" + v4Cap + ") " +
"{\n (" + v4t2 + ") 116,\n (" + v4t2 + ") 101,\n (" + v4t2 +
") 115,\n (" + v4t2 + ") 116,\n (" + v4t2 + ") 52,\n (" + v4t2 +
") 0\n}"
addDumpTest(v4, "("+v4t+") "+v4s+"\n")
// C uint8_t array.
v5, v5l, v5c := testdata.GetCgoUint8tArray()
v5Len := fmt.Sprintf("%d", v5l)
v5Cap := fmt.Sprintf("%d", v5c)
v5t := "[6]testdata._Ctype_uint8_t"
v5s := "(len=" + v5Len + " cap=" + v5Cap + ") " +
"{\n 00000000 74 65 73 74 35 00 " +
" |test5.|\n}"
addDumpTest(v5, "("+v5t+") "+v5s+"\n")
// C typedefed unsigned char array.
v6, v6l, v6c := testdata.GetCgoTypdefedUnsignedCharArray()
v6Len := fmt.Sprintf("%d", v6l)
v6Cap := fmt.Sprintf("%d", v6c)
v6t := "[6]testdata._Ctype_custom_uchar_t"
v6s := "(len=" + v6Len + " cap=" + v6Cap + ") " +
"{\n 00000000 74 65 73 74 36 00 " +
" |test6.|\n}"
addDumpTest(v6, "("+v6t+") "+v6s+"\n")
}

View File

@ -0,0 +1,26 @@
// Copyright (c) 2013 Dave Collins <dave@davec.name>
//
// Permission to use, copy, modify, and distribute this software for any
// purpose with or without fee is hereby granted, provided that the above
// copyright notice and this permission notice appear in all copies.
//
// THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
// WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
// MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
// ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
// WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
// ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
// OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
// NOTE: Due to the following build constraints, this file will only be compiled
// when either cgo is not supported or "-tags testcgo" is not added to the go
// test command line. This file intentionally does not setup any cgo tests in
// this scenario.
// +build !cgo !testcgo
package spew_test
func addCgoDumpTests() {
// Don't add any tests for cgo since this file is only compiled when
// there should not be any cgo tests.
}

View File

@ -0,0 +1,230 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew_test
import (
"fmt"
"github.com/davecgh/go-spew/spew"
)
type Flag int
const (
flagOne Flag = iota
flagTwo
)
var flagStrings = map[Flag]string{
flagOne: "flagOne",
flagTwo: "flagTwo",
}
func (f Flag) String() string {
if s, ok := flagStrings[f]; ok {
return s
}
return fmt.Sprintf("Unknown flag (%d)", int(f))
}
type Bar struct {
flag Flag
data uintptr
}
type Foo struct {
unexportedField Bar
ExportedField map[interface{}]interface{}
}
// This example demonstrates how to use Dump to dump variables to stdout.
func ExampleDump() {
// The following package level declarations are assumed for this example:
/*
type Flag int
const (
flagOne Flag = iota
flagTwo
)
var flagStrings = map[Flag]string{
flagOne: "flagOne",
flagTwo: "flagTwo",
}
func (f Flag) String() string {
if s, ok := flagStrings[f]; ok {
return s
}
return fmt.Sprintf("Unknown flag (%d)", int(f))
}
type Bar struct {
flag Flag
data uintptr
}
type Foo struct {
unexportedField Bar
ExportedField map[interface{}]interface{}
}
*/
// Setup some sample data structures for the example.
bar := Bar{Flag(flagTwo), uintptr(0)}
s1 := Foo{bar, map[interface{}]interface{}{"one": true}}
f := Flag(5)
b := []byte{
0x11, 0x12, 0x13, 0x14, 0x15, 0x16, 0x17, 0x18,
0x19, 0x1a, 0x1b, 0x1c, 0x1d, 0x1e, 0x1f, 0x20,
0x21, 0x22, 0x23, 0x24, 0x25, 0x26, 0x27, 0x28,
0x29, 0x2a, 0x2b, 0x2c, 0x2d, 0x2e, 0x2f, 0x30,
0x31, 0x32,
}
// Dump!
spew.Dump(s1, f, b)
// Output:
// (spew_test.Foo) {
// unexportedField: (spew_test.Bar) {
// flag: (spew_test.Flag) flagTwo,
// data: (uintptr) <nil>
// },
// ExportedField: (map[interface {}]interface {}) (len=1) {
// (string) (len=3) "one": (bool) true
// }
// }
// (spew_test.Flag) Unknown flag (5)
// ([]uint8) (len=34 cap=34) {
// 00000000 11 12 13 14 15 16 17 18 19 1a 1b 1c 1d 1e 1f 20 |............... |
// 00000010 21 22 23 24 25 26 27 28 29 2a 2b 2c 2d 2e 2f 30 |!"#$%&'()*+,-./0|
// 00000020 31 32 |12|
// }
//
}
// This example demonstrates how to use Printf to display a variable with a
// format string and inline formatting.
func ExamplePrintf() {
// Create a double pointer to a uint 8.
ui8 := uint8(5)
pui8 := &ui8
ppui8 := &pui8
// Create a circular data type.
type circular struct {
ui8 uint8
c *circular
}
c := circular{ui8: 1}
c.c = &c
// Print!
spew.Printf("ppui8: %v\n", ppui8)
spew.Printf("circular: %v\n", c)
// Output:
// ppui8: <**>5
// circular: {1 <*>{1 <*><shown>}}
}
// This example demonstrates how to use a ConfigState.
func ExampleConfigState() {
// Modify the indent level of the ConfigState only. The global
// configuration is not modified.
scs := spew.ConfigState{Indent: "\t"}
// Output using the ConfigState instance.
v := map[string]int{"one": 1}
scs.Printf("v: %v\n", v)
scs.Dump(v)
// Output:
// v: map[one:1]
// (map[string]int) (len=1) {
// (string) (len=3) "one": (int) 1
// }
}
// This example demonstrates how to use ConfigState.Dump to dump variables to
// stdout
func ExampleConfigState_Dump() {
// See the top-level Dump example for details on the types used in this
// example.
// Create two ConfigState instances with different indentation.
scs := spew.ConfigState{Indent: "\t"}
scs2 := spew.ConfigState{Indent: " "}
// Setup some sample data structures for the example.
bar := Bar{Flag(flagTwo), uintptr(0)}
s1 := Foo{bar, map[interface{}]interface{}{"one": true}}
// Dump using the ConfigState instances.
scs.Dump(s1)
scs2.Dump(s1)
// Output:
// (spew_test.Foo) {
// unexportedField: (spew_test.Bar) {
// flag: (spew_test.Flag) flagTwo,
// data: (uintptr) <nil>
// },
// ExportedField: (map[interface {}]interface {}) (len=1) {
// (string) (len=3) "one": (bool) true
// }
// }
// (spew_test.Foo) {
// unexportedField: (spew_test.Bar) {
// flag: (spew_test.Flag) flagTwo,
// data: (uintptr) <nil>
// },
// ExportedField: (map[interface {}]interface {}) (len=1) {
// (string) (len=3) "one": (bool) true
// }
// }
//
}
// This example demonstrates how to use ConfigState.Printf to display a variable
// with a format string and inline formatting.
func ExampleConfigState_Printf() {
// See the top-level Dump example for details on the types used in this
// example.
// Create two ConfigState instances and modify the method handling of the
// first ConfigState only.
scs := spew.NewDefaultConfig()
scs2 := spew.NewDefaultConfig()
scs.DisableMethods = true
// Alternatively
// scs := spew.ConfigState{Indent: " ", DisableMethods: true}
// scs2 := spew.ConfigState{Indent: " "}
// This is of type Flag which implements a Stringer and has raw value 1.
f := flagTwo
// Dump using the ConfigState instances.
scs.Printf("f: %v\n", f)
scs2.Printf("f: %v\n", f)
// Output:
// f: 1
// f: flagTwo
}

View File

@ -0,0 +1,419 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew
import (
"bytes"
"fmt"
"reflect"
"strconv"
"strings"
)
// supportedFlags is a list of all the character flags supported by fmt package.
const supportedFlags = "0-+# "
// formatState implements the fmt.Formatter interface and contains information
// about the state of a formatting operation. The NewFormatter function can
// be used to get a new Formatter which can be used directly as arguments
// in standard fmt package printing calls.
type formatState struct {
value interface{}
fs fmt.State
depth int
pointers map[uintptr]int
ignoreNextType bool
cs *ConfigState
}
// buildDefaultFormat recreates the original format string without precision
// and width information to pass in to fmt.Sprintf in the case of an
// unrecognized type. Unless new types are added to the language, this
// function won't ever be called.
func (f *formatState) buildDefaultFormat() (format string) {
buf := bytes.NewBuffer(percentBytes)
for _, flag := range supportedFlags {
if f.fs.Flag(int(flag)) {
buf.WriteRune(flag)
}
}
buf.WriteRune('v')
format = buf.String()
return format
}
// constructOrigFormat recreates the original format string including precision
// and width information to pass along to the standard fmt package. This allows
// automatic deferral of all format strings this package doesn't support.
func (f *formatState) constructOrigFormat(verb rune) (format string) {
buf := bytes.NewBuffer(percentBytes)
for _, flag := range supportedFlags {
if f.fs.Flag(int(flag)) {
buf.WriteRune(flag)
}
}
if width, ok := f.fs.Width(); ok {
buf.WriteString(strconv.Itoa(width))
}
if precision, ok := f.fs.Precision(); ok {
buf.Write(precisionBytes)
buf.WriteString(strconv.Itoa(precision))
}
buf.WriteRune(verb)
format = buf.String()
return format
}
// unpackValue returns values inside of non-nil interfaces when possible and
// ensures that types for values which have been unpacked from an interface
// are displayed when the show types flag is also set.
// This is useful for data types like structs, arrays, slices, and maps which
// can contain varying types packed inside an interface.
func (f *formatState) unpackValue(v reflect.Value) reflect.Value {
if v.Kind() == reflect.Interface {
f.ignoreNextType = false
if !v.IsNil() {
v = v.Elem()
}
}
return v
}
// formatPtr handles formatting of pointers by indirecting them as necessary.
func (f *formatState) formatPtr(v reflect.Value) {
// Display nil if top level pointer is nil.
showTypes := f.fs.Flag('#')
if v.IsNil() && (!showTypes || f.ignoreNextType) {
f.fs.Write(nilAngleBytes)
return
}
// Remove pointers at or below the current depth from map used to detect
// circular refs.
for k, depth := range f.pointers {
if depth >= f.depth {
delete(f.pointers, k)
}
}
// Keep list of all dereferenced pointers to possibly show later.
pointerChain := make([]uintptr, 0)
// Figure out how many levels of indirection there are by derferencing
// pointers and unpacking interfaces down the chain while detecting circular
// references.
nilFound := false
cycleFound := false
indirects := 0
ve := v
for ve.Kind() == reflect.Ptr {
if ve.IsNil() {
nilFound = true
break
}
indirects++
addr := ve.Pointer()
pointerChain = append(pointerChain, addr)
if pd, ok := f.pointers[addr]; ok && pd < f.depth {
cycleFound = true
indirects--
break
}
f.pointers[addr] = f.depth
ve = ve.Elem()
if ve.Kind() == reflect.Interface {
if ve.IsNil() {
nilFound = true
break
}
ve = ve.Elem()
}
}
// Display type or indirection level depending on flags.
if showTypes && !f.ignoreNextType {
f.fs.Write(openParenBytes)
f.fs.Write(bytes.Repeat(asteriskBytes, indirects))
f.fs.Write([]byte(ve.Type().String()))
f.fs.Write(closeParenBytes)
} else {
if nilFound || cycleFound {
indirects += strings.Count(ve.Type().String(), "*")
}
f.fs.Write(openAngleBytes)
f.fs.Write([]byte(strings.Repeat("*", indirects)))
f.fs.Write(closeAngleBytes)
}
// Display pointer information depending on flags.
if f.fs.Flag('+') && (len(pointerChain) > 0) {
f.fs.Write(openParenBytes)
for i, addr := range pointerChain {
if i > 0 {
f.fs.Write(pointerChainBytes)
}
printHexPtr(f.fs, addr)
}
f.fs.Write(closeParenBytes)
}
// Display dereferenced value.
switch {
case nilFound == true:
f.fs.Write(nilAngleBytes)
case cycleFound == true:
f.fs.Write(circularShortBytes)
default:
f.ignoreNextType = true
f.format(ve)
}
}
// format is the main workhorse for providing the Formatter interface. It
// uses the passed reflect value to figure out what kind of object we are
// dealing with and formats it appropriately. It is a recursive function,
// however circular data structures are detected and handled properly.
func (f *formatState) format(v reflect.Value) {
// Handle invalid reflect values immediately.
kind := v.Kind()
if kind == reflect.Invalid {
f.fs.Write(invalidAngleBytes)
return
}
// Handle pointers specially.
if kind == reflect.Ptr {
f.formatPtr(v)
return
}
// Print type information unless already handled elsewhere.
if !f.ignoreNextType && f.fs.Flag('#') {
f.fs.Write(openParenBytes)
f.fs.Write([]byte(v.Type().String()))
f.fs.Write(closeParenBytes)
}
f.ignoreNextType = false
// Call Stringer/error interfaces if they exist and the handle methods
// flag is enabled.
if !f.cs.DisableMethods {
if (kind != reflect.Invalid) && (kind != reflect.Interface) {
if handled := handleMethods(f.cs, f.fs, v); handled {
return
}
}
}
switch kind {
case reflect.Invalid:
// Do nothing. We should never get here since invalid has already
// been handled above.
case reflect.Bool:
printBool(f.fs, v.Bool())
case reflect.Int8, reflect.Int16, reflect.Int32, reflect.Int64, reflect.Int:
printInt(f.fs, v.Int(), 10)
case reflect.Uint8, reflect.Uint16, reflect.Uint32, reflect.Uint64, reflect.Uint:
printUint(f.fs, v.Uint(), 10)
case reflect.Float32:
printFloat(f.fs, v.Float(), 32)
case reflect.Float64:
printFloat(f.fs, v.Float(), 64)
case reflect.Complex64:
printComplex(f.fs, v.Complex(), 32)
case reflect.Complex128:
printComplex(f.fs, v.Complex(), 64)
case reflect.Slice:
if v.IsNil() {
f.fs.Write(nilAngleBytes)
break
}
fallthrough
case reflect.Array:
f.fs.Write(openBracketBytes)
f.depth++
if (f.cs.MaxDepth != 0) && (f.depth > f.cs.MaxDepth) {
f.fs.Write(maxShortBytes)
} else {
numEntries := v.Len()
for i := 0; i < numEntries; i++ {
if i > 0 {
f.fs.Write(spaceBytes)
}
f.ignoreNextType = true
f.format(f.unpackValue(v.Index(i)))
}
}
f.depth--
f.fs.Write(closeBracketBytes)
case reflect.String:
f.fs.Write([]byte(v.String()))
case reflect.Interface:
// The only time we should get here is for nil interfaces due to
// unpackValue calls.
if v.IsNil() {
f.fs.Write(nilAngleBytes)
}
case reflect.Ptr:
// Do nothing. We should never get here since pointers have already
// been handled above.
case reflect.Map:
// nil maps should be indicated as different than empty maps
if v.IsNil() {
f.fs.Write(nilAngleBytes)
break
}
f.fs.Write(openMapBytes)
f.depth++
if (f.cs.MaxDepth != 0) && (f.depth > f.cs.MaxDepth) {
f.fs.Write(maxShortBytes)
} else {
keys := v.MapKeys()
if f.cs.SortKeys {
sortValues(keys, f.cs)
}
for i, key := range keys {
if i > 0 {
f.fs.Write(spaceBytes)
}
f.ignoreNextType = true
f.format(f.unpackValue(key))
f.fs.Write(colonBytes)
f.ignoreNextType = true
f.format(f.unpackValue(v.MapIndex(key)))
}
}
f.depth--
f.fs.Write(closeMapBytes)
case reflect.Struct:
numFields := v.NumField()
f.fs.Write(openBraceBytes)
f.depth++
if (f.cs.MaxDepth != 0) && (f.depth > f.cs.MaxDepth) {
f.fs.Write(maxShortBytes)
} else {
vt := v.Type()
for i := 0; i < numFields; i++ {
if i > 0 {
f.fs.Write(spaceBytes)
}
vtf := vt.Field(i)
if f.fs.Flag('+') || f.fs.Flag('#') {
f.fs.Write([]byte(vtf.Name))
f.fs.Write(colonBytes)
}
f.format(f.unpackValue(v.Field(i)))
}
}
f.depth--
f.fs.Write(closeBraceBytes)
case reflect.Uintptr:
printHexPtr(f.fs, uintptr(v.Uint()))
case reflect.UnsafePointer, reflect.Chan, reflect.Func:
printHexPtr(f.fs, v.Pointer())
// There were not any other types at the time this code was written, but
// fall back to letting the default fmt package handle it if any get added.
default:
format := f.buildDefaultFormat()
if v.CanInterface() {
fmt.Fprintf(f.fs, format, v.Interface())
} else {
fmt.Fprintf(f.fs, format, v.String())
}
}
}
// Format satisfies the fmt.Formatter interface. See NewFormatter for usage
// details.
func (f *formatState) Format(fs fmt.State, verb rune) {
f.fs = fs
// Use standard formatting for verbs that are not v.
if verb != 'v' {
format := f.constructOrigFormat(verb)
fmt.Fprintf(fs, format, f.value)
return
}
if f.value == nil {
if fs.Flag('#') {
fs.Write(interfaceBytes)
}
fs.Write(nilAngleBytes)
return
}
f.format(reflect.ValueOf(f.value))
}
// newFormatter is a helper function to consolidate the logic from the various
// public methods which take varying config states.
func newFormatter(cs *ConfigState, v interface{}) fmt.Formatter {
fs := &formatState{value: v, cs: cs}
fs.pointers = make(map[uintptr]int)
return fs
}
/*
NewFormatter returns a custom formatter that satisfies the fmt.Formatter
interface. As a result, it integrates cleanly with standard fmt package
printing functions. The formatter is useful for inline printing of smaller data
types similar to the standard %v format specifier.
The custom formatter only responds to the %v (most compact), %+v (adds pointer
addresses), %#v (adds types), or %#+v (adds types and pointer addresses) verb
combinations. Any other verbs such as %x and %q will be sent to the the
standard fmt package for formatting. In addition, the custom formatter ignores
the width and precision arguments (however they will still work on the format
specifiers not handled by the custom formatter).
Typically this function shouldn't be called directly. It is much easier to make
use of the custom formatter by calling one of the convenience functions such as
Printf, Println, or Fprintf.
*/
func NewFormatter(v interface{}) fmt.Formatter {
return newFormatter(&Config, v)
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,156 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
/*
This test file is part of the spew package rather than than the spew_test
package because it needs access to internals to properly test certain cases
which are not possible via the public interface since they should never happen.
*/
package spew
import (
"bytes"
"reflect"
"testing"
"unsafe"
)
// dummyFmtState implements a fake fmt.State to use for testing invalid
// reflect.Value handling. This is necessary because the fmt package catches
// invalid values before invoking the formatter on them.
type dummyFmtState struct {
bytes.Buffer
}
func (dfs *dummyFmtState) Flag(f int) bool {
if f == int('+') {
return true
}
return false
}
func (dfs *dummyFmtState) Precision() (int, bool) {
return 0, false
}
func (dfs *dummyFmtState) Width() (int, bool) {
return 0, false
}
// TestInvalidReflectValue ensures the dump and formatter code handles an
// invalid reflect value properly. This needs access to internal state since it
// should never happen in real code and therefore can't be tested via the public
// API.
func TestInvalidReflectValue(t *testing.T) {
i := 1
// Dump invalid reflect value.
v := new(reflect.Value)
buf := new(bytes.Buffer)
d := dumpState{w: buf, cs: &Config}
d.dump(*v)
s := buf.String()
want := "<invalid>"
if s != want {
t.Errorf("InvalidReflectValue #%d\n got: %s want: %s", i, s, want)
}
i++
// Formatter invalid reflect value.
buf2 := new(dummyFmtState)
f := formatState{value: *v, cs: &Config, fs: buf2}
f.format(*v)
s = buf2.String()
want = "<invalid>"
if s != want {
t.Errorf("InvalidReflectValue #%d got: %s want: %s", i, s, want)
}
}
// changeKind uses unsafe to intentionally change the kind of a reflect.Value to
// the maximum kind value which does not exist. This is needed to test the
// fallback code which punts to the standard fmt library for new types that
// might get added to the language.
func changeKind(v *reflect.Value, readOnly bool) {
rvf := (*uintptr)(unsafe.Pointer(uintptr(unsafe.Pointer(v)) + offsetFlag))
*rvf = *rvf | ((1<<flagKindWidth - 1) << flagKindShift)
if readOnly {
*rvf |= flagRO
} else {
*rvf &= ^uintptr(flagRO)
}
}
// TestAddedReflectValue tests functionaly of the dump and formatter code which
// falls back to the standard fmt library for new types that might get added to
// the language.
func TestAddedReflectValue(t *testing.T) {
i := 1
// Dump using a reflect.Value that is exported.
v := reflect.ValueOf(int8(5))
changeKind(&v, false)
buf := new(bytes.Buffer)
d := dumpState{w: buf, cs: &Config}
d.dump(v)
s := buf.String()
want := "(int8) 5"
if s != want {
t.Errorf("TestAddedReflectValue #%d\n got: %s want: %s", i, s, want)
}
i++
// Dump using a reflect.Value that is not exported.
changeKind(&v, true)
buf.Reset()
d.dump(v)
s = buf.String()
want = "(int8) <int8 Value>"
if s != want {
t.Errorf("TestAddedReflectValue #%d\n got: %s want: %s", i, s, want)
}
i++
// Formatter using a reflect.Value that is exported.
changeKind(&v, false)
buf2 := new(dummyFmtState)
f := formatState{value: v, cs: &Config, fs: buf2}
f.format(v)
s = buf2.String()
want = "5"
if s != want {
t.Errorf("TestAddedReflectValue #%d got: %s want: %s", i, s, want)
}
i++
// Formatter using a reflect.Value that is not exported.
changeKind(&v, true)
buf2.Reset()
f = formatState{value: v, cs: &Config, fs: buf2}
f.format(v)
s = buf2.String()
want = "<int8 Value>"
if s != want {
t.Errorf("TestAddedReflectValue #%d got: %s want: %s", i, s, want)
}
}
// SortValues makes the internal sortValues function available to the test
// package.
func SortValues(values []reflect.Value, cs *ConfigState) {
sortValues(values, cs)
}

View File

@ -0,0 +1,148 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew
import (
"fmt"
"io"
)
// Errorf is a wrapper for fmt.Errorf that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the formatted string as a value that satisfies error. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Errorf(format, spew.NewFormatter(a), spew.NewFormatter(b))
func Errorf(format string, a ...interface{}) (err error) {
return fmt.Errorf(format, convertArgs(a)...)
}
// Fprint is a wrapper for fmt.Fprint that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprint(w, spew.NewFormatter(a), spew.NewFormatter(b))
func Fprint(w io.Writer, a ...interface{}) (n int, err error) {
return fmt.Fprint(w, convertArgs(a)...)
}
// Fprintf is a wrapper for fmt.Fprintf that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprintf(w, format, spew.NewFormatter(a), spew.NewFormatter(b))
func Fprintf(w io.Writer, format string, a ...interface{}) (n int, err error) {
return fmt.Fprintf(w, format, convertArgs(a)...)
}
// Fprintln is a wrapper for fmt.Fprintln that treats each argument as if it
// passed with a default Formatter interface returned by NewFormatter. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Fprintln(w, spew.NewFormatter(a), spew.NewFormatter(b))
func Fprintln(w io.Writer, a ...interface{}) (n int, err error) {
return fmt.Fprintln(w, convertArgs(a)...)
}
// Print is a wrapper for fmt.Print that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Print(spew.NewFormatter(a), spew.NewFormatter(b))
func Print(a ...interface{}) (n int, err error) {
return fmt.Print(convertArgs(a)...)
}
// Printf is a wrapper for fmt.Printf that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Printf(format, spew.NewFormatter(a), spew.NewFormatter(b))
func Printf(format string, a ...interface{}) (n int, err error) {
return fmt.Printf(format, convertArgs(a)...)
}
// Println is a wrapper for fmt.Println that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the number of bytes written and any write error encountered. See
// NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Println(spew.NewFormatter(a), spew.NewFormatter(b))
func Println(a ...interface{}) (n int, err error) {
return fmt.Println(convertArgs(a)...)
}
// Sprint is a wrapper for fmt.Sprint that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprint(spew.NewFormatter(a), spew.NewFormatter(b))
func Sprint(a ...interface{}) string {
return fmt.Sprint(convertArgs(a)...)
}
// Sprintf is a wrapper for fmt.Sprintf that treats each argument as if it were
// passed with a default Formatter interface returned by NewFormatter. It
// returns the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprintf(format, spew.NewFormatter(a), spew.NewFormatter(b))
func Sprintf(format string, a ...interface{}) string {
return fmt.Sprintf(format, convertArgs(a)...)
}
// Sprintln is a wrapper for fmt.Sprintln that treats each argument as if it
// were passed with a default Formatter interface returned by NewFormatter. It
// returns the resulting string. See NewFormatter for formatting details.
//
// This function is shorthand for the following syntax:
//
// fmt.Sprintln(spew.NewFormatter(a), spew.NewFormatter(b))
func Sprintln(a ...interface{}) string {
return fmt.Sprintln(convertArgs(a)...)
}
// convertArgs accepts a slice of arguments and returns a slice of the same
// length with each argument converted to a default spew Formatter interface.
func convertArgs(args []interface{}) (formatters []interface{}) {
formatters = make([]interface{}, len(args))
for index, arg := range args {
formatters[index] = NewFormatter(arg)
}
return formatters
}

View File

@ -0,0 +1,308 @@
/*
* Copyright (c) 2013 Dave Collins <dave@davec.name>
*
* Permission to use, copy, modify, and distribute this software for any
* purpose with or without fee is hereby granted, provided that the above
* copyright notice and this permission notice appear in all copies.
*
* THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
* WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
* MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
* ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
* WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
* ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
* OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
*/
package spew_test
import (
"bytes"
"fmt"
"github.com/davecgh/go-spew/spew"
"io/ioutil"
"os"
"testing"
)
// spewFunc is used to identify which public function of the spew package or
// ConfigState a test applies to.
type spewFunc int
const (
fCSFdump spewFunc = iota
fCSFprint
fCSFprintf
fCSFprintln
fCSPrint
fCSPrintln
fCSSdump
fCSSprint
fCSSprintf
fCSSprintln
fCSErrorf
fCSNewFormatter
fErrorf
fFprint
fFprintln
fPrint
fPrintln
fSdump
fSprint
fSprintf
fSprintln
)
// Map of spewFunc values to names for pretty printing.
var spewFuncStrings = map[spewFunc]string{
fCSFdump: "ConfigState.Fdump",
fCSFprint: "ConfigState.Fprint",
fCSFprintf: "ConfigState.Fprintf",
fCSFprintln: "ConfigState.Fprintln",
fCSSdump: "ConfigState.Sdump",
fCSPrint: "ConfigState.Print",
fCSPrintln: "ConfigState.Println",
fCSSprint: "ConfigState.Sprint",
fCSSprintf: "ConfigState.Sprintf",
fCSSprintln: "ConfigState.Sprintln",
fCSErrorf: "ConfigState.Errorf",
fCSNewFormatter: "ConfigState.NewFormatter",
fErrorf: "spew.Errorf",
fFprint: "spew.Fprint",
fFprintln: "spew.Fprintln",
fPrint: "spew.Print",
fPrintln: "spew.Println",
fSdump: "spew.Sdump",
fSprint: "spew.Sprint",
fSprintf: "spew.Sprintf",
fSprintln: "spew.Sprintln",
}
func (f spewFunc) String() string {
if s, ok := spewFuncStrings[f]; ok {
return s
}
return fmt.Sprintf("Unknown spewFunc (%d)", int(f))
}
// spewTest is used to describe a test to be performed against the public
// functions of the spew package or ConfigState.
type spewTest struct {
cs *spew.ConfigState
f spewFunc
format string
in interface{}
want string
}
// spewTests houses the tests to be performed against the public functions of
// the spew package and ConfigState.
//
// These tests are only intended to ensure the public functions are exercised
// and are intentionally not exhaustive of types. The exhaustive type
// tests are handled in the dump and format tests.
var spewTests []spewTest
// redirStdout is a helper function to return the standard output from f as a
// byte slice.
func redirStdout(f func()) ([]byte, error) {
tempFile, err := ioutil.TempFile("", "ss-test")
if err != nil {
return nil, err
}
fileName := tempFile.Name()
defer os.Remove(fileName) // Ignore error
origStdout := os.Stdout
os.Stdout = tempFile
f()
os.Stdout = origStdout
tempFile.Close()
return ioutil.ReadFile(fileName)
}
func initSpewTests() {
// Config states with various settings.
scsDefault := spew.NewDefaultConfig()
scsNoMethods := &spew.ConfigState{Indent: " ", DisableMethods: true}
scsNoPmethods := &spew.ConfigState{Indent: " ", DisablePointerMethods: true}
scsMaxDepth := &spew.ConfigState{Indent: " ", MaxDepth: 1}
scsContinue := &spew.ConfigState{Indent: " ", ContinueOnMethod: true}
// Variables for tests on types which implement Stringer interface with and
// without a pointer receiver.
ts := stringer("test")
tps := pstringer("test")
// depthTester is used to test max depth handling for structs, array, slices
// and maps.
type depthTester struct {
ic indirCir1
arr [1]string
slice []string
m map[string]int
}
dt := depthTester{indirCir1{nil}, [1]string{"arr"}, []string{"slice"},
map[string]int{"one": 1}}
// Variable for tests on types which implement error interface.
te := customError(10)
spewTests = []spewTest{
{scsDefault, fCSFdump, "", int8(127), "(int8) 127\n"},
{scsDefault, fCSFprint, "", int16(32767), "32767"},
{scsDefault, fCSFprintf, "%v", int32(2147483647), "2147483647"},
{scsDefault, fCSFprintln, "", int(2147483647), "2147483647\n"},
{scsDefault, fCSPrint, "", int64(9223372036854775807), "9223372036854775807"},
{scsDefault, fCSPrintln, "", uint8(255), "255\n"},
{scsDefault, fCSSdump, "", uint8(64), "(uint8) 64\n"},
{scsDefault, fCSSprint, "", complex(1, 2), "(1+2i)"},
{scsDefault, fCSSprintf, "%v", complex(float32(3), 4), "(3+4i)"},
{scsDefault, fCSSprintln, "", complex(float64(5), 6), "(5+6i)\n"},
{scsDefault, fCSErrorf, "%#v", uint16(65535), "(uint16)65535"},
{scsDefault, fCSNewFormatter, "%v", uint32(4294967295), "4294967295"},
{scsDefault, fErrorf, "%v", uint64(18446744073709551615), "18446744073709551615"},
{scsDefault, fFprint, "", float32(3.14), "3.14"},
{scsDefault, fFprintln, "", float64(6.28), "6.28\n"},
{scsDefault, fPrint, "", true, "true"},
{scsDefault, fPrintln, "", false, "false\n"},
{scsDefault, fSdump, "", complex(-10, -20), "(complex128) (-10-20i)\n"},
{scsDefault, fSprint, "", complex(-1, -2), "(-1-2i)"},
{scsDefault, fSprintf, "%v", complex(float32(-3), -4), "(-3-4i)"},
{scsDefault, fSprintln, "", complex(float64(-5), -6), "(-5-6i)\n"},
{scsNoMethods, fCSFprint, "", ts, "test"},
{scsNoMethods, fCSFprint, "", &ts, "<*>test"},
{scsNoMethods, fCSFprint, "", tps, "test"},
{scsNoMethods, fCSFprint, "", &tps, "<*>test"},
{scsNoPmethods, fCSFprint, "", ts, "stringer test"},
{scsNoPmethods, fCSFprint, "", &ts, "<*>stringer test"},
{scsNoPmethods, fCSFprint, "", tps, "test"},
{scsNoPmethods, fCSFprint, "", &tps, "<*>stringer test"},
{scsMaxDepth, fCSFprint, "", dt, "{{<max>} [<max>] [<max>] map[<max>]}"},
{scsMaxDepth, fCSFdump, "", dt, "(spew_test.depthTester) {\n" +
" ic: (spew_test.indirCir1) {\n <max depth reached>\n },\n" +
" arr: ([1]string) (len=1 cap=1) {\n <max depth reached>\n },\n" +
" slice: ([]string) (len=1 cap=1) {\n <max depth reached>\n },\n" +
" m: (map[string]int) (len=1) {\n <max depth reached>\n }\n}\n"},
{scsContinue, fCSFprint, "", ts, "(stringer test) test"},
{scsContinue, fCSFdump, "", ts, "(spew_test.stringer) " +
"(len=4) (stringer test) \"test\"\n"},
{scsContinue, fCSFprint, "", te, "(error: 10) 10"},
{scsContinue, fCSFdump, "", te, "(spew_test.customError) " +
"(error: 10) 10\n"},
}
}
// TestSpew executes all of the tests described by spewTests.
func TestSpew(t *testing.T) {
initSpewTests()
t.Logf("Running %d tests", len(spewTests))
for i, test := range spewTests {
buf := new(bytes.Buffer)
switch test.f {
case fCSFdump:
test.cs.Fdump(buf, test.in)
case fCSFprint:
test.cs.Fprint(buf, test.in)
case fCSFprintf:
test.cs.Fprintf(buf, test.format, test.in)
case fCSFprintln:
test.cs.Fprintln(buf, test.in)
case fCSPrint:
b, err := redirStdout(func() { test.cs.Print(test.in) })
if err != nil {
t.Errorf("%v #%d %v", test.f, i, err)
continue
}
buf.Write(b)
case fCSPrintln:
b, err := redirStdout(func() { test.cs.Println(test.in) })
if err != nil {
t.Errorf("%v #%d %v", test.f, i, err)
continue
}
buf.Write(b)
case fCSSdump:
str := test.cs.Sdump(test.in)
buf.WriteString(str)
case fCSSprint:
str := test.cs.Sprint(test.in)
buf.WriteString(str)
case fCSSprintf:
str := test.cs.Sprintf(test.format, test.in)
buf.WriteString(str)
case fCSSprintln:
str := test.cs.Sprintln(test.in)
buf.WriteString(str)
case fCSErrorf:
err := test.cs.Errorf(test.format, test.in)
buf.WriteString(err.Error())
case fCSNewFormatter:
fmt.Fprintf(buf, test.format, test.cs.NewFormatter(test.in))
case fErrorf:
err := spew.Errorf(test.format, test.in)
buf.WriteString(err.Error())
case fFprint:
spew.Fprint(buf, test.in)
case fFprintln:
spew.Fprintln(buf, test.in)
case fPrint:
b, err := redirStdout(func() { spew.Print(test.in) })
if err != nil {
t.Errorf("%v #%d %v", test.f, i, err)
continue
}
buf.Write(b)
case fPrintln:
b, err := redirStdout(func() { spew.Println(test.in) })
if err != nil {
t.Errorf("%v #%d %v", test.f, i, err)
continue
}
buf.Write(b)
case fSdump:
str := spew.Sdump(test.in)
buf.WriteString(str)
case fSprint:
str := spew.Sprint(test.in)
buf.WriteString(str)
case fSprintf:
str := spew.Sprintf(test.format, test.in)
buf.WriteString(str)
case fSprintln:
str := spew.Sprintln(test.in)
buf.WriteString(str)
default:
t.Errorf("%v #%d unrecognized function", test.f, i)
continue
}
s := buf.String()
if test.want != s {
t.Errorf("ConfigState #%d\n got: %s want: %s", i, s, test.want)
continue
}
}
}

View File

@ -0,0 +1,82 @@
// Copyright (c) 2013 Dave Collins <dave@davec.name>
//
// Permission to use, copy, modify, and distribute this software for any
// purpose with or without fee is hereby granted, provided that the above
// copyright notice and this permission notice appear in all copies.
//
// THE SOFTWARE IS PROVIDED "AS IS" AND THE AUTHOR DISCLAIMS ALL WARRANTIES
// WITH REGARD TO THIS SOFTWARE INCLUDING ALL IMPLIED WARRANTIES OF
// MERCHANTABILITY AND FITNESS. IN NO EVENT SHALL THE AUTHOR BE LIABLE FOR
// ANY SPECIAL, DIRECT, INDIRECT, OR CONSEQUENTIAL DAMAGES OR ANY DAMAGES
// WHATSOEVER RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN
// ACTION OF CONTRACT, NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF
// OR IN CONNECTION WITH THE USE OR PERFORMANCE OF THIS SOFTWARE.
// NOTE: Due to the following build constraints, this file will only be compiled
// when both cgo is supported and "-tags testcgo" is added to the go test
// command line. This code should really only be in the dumpcgo_test.go file,
// but unfortunately Go will not allow cgo in test files, so this is a
// workaround to allow cgo types to be tested. This configuration is used
// because spew itself does not require cgo to run even though it does handle
// certain cgo types specially. Rather than forcing all clients to require cgo
// and an external C compiler just to run the tests, this scheme makes them
// optional.
// +build cgo,testcgo
package testdata
/*
#include <stdint.h>
typedef unsigned char custom_uchar_t;
char *ncp = 0;
char *cp = "test";
char ca[6] = {'t', 'e', 's', 't', '2', '\0'};
unsigned char uca[6] = {'t', 'e', 's', 't', '3', '\0'};
signed char sca[6] = {'t', 'e', 's', 't', '4', '\0'};
uint8_t ui8ta[6] = {'t', 'e', 's', 't', '5', '\0'};
custom_uchar_t tuca[6] = {'t', 'e', 's', 't', '6', '\0'};
*/
import "C"
// GetCgoNullCharPointer returns a null char pointer via cgo. This is only
// used for tests.
func GetCgoNullCharPointer() interface{} {
return C.ncp
}
// GetCgoCharPointer returns a char pointer via cgo. This is only used for
// tests.
func GetCgoCharPointer() interface{} {
return C.cp
}
// GetCgoCharArray returns a char array via cgo and the array's len and cap.
// This is only used for tests.
func GetCgoCharArray() (interface{}, int, int) {
return C.ca, len(C.ca), cap(C.ca)
}
// GetCgoUnsignedCharArray returns an unsigned char array via cgo and the
// array's len and cap. This is only used for tests.
func GetCgoUnsignedCharArray() (interface{}, int, int) {
return C.uca, len(C.uca), cap(C.uca)
}
// GetCgoSignedCharArray returns a signed char array via cgo and the array's len
// and cap. This is only used for tests.
func GetCgoSignedCharArray() (interface{}, int, int) {
return C.sca, len(C.sca), cap(C.sca)
}
// GetCgoUint8tArray returns a uint8_t array via cgo and the array's len and
// cap. This is only used for tests.
func GetCgoUint8tArray() (interface{}, int, int) {
return C.ui8ta, len(C.ui8ta), cap(C.ui8ta)
}
// GetCgoTypdefedUnsignedCharArray returns a typedefed unsigned char array via
// cgo and the array's len and cap. This is only used for tests.
func GetCgoTypdefedUnsignedCharArray() (interface{}, int, int) {
return C.tuca, len(C.tuca), cap(C.tuca)
}

View File

@ -18,6 +18,7 @@ import (
"path/filepath" "path/filepath"
"runtime" "runtime"
"sync" "sync"
"sync/atomic"
"time" "time"
"unsafe" "unsafe"
@ -235,7 +236,7 @@ type Full struct {
test bool // if set use a smaller DAG size test bool // if set use a smaller DAG size
turbo bool turbo bool
hashRate int64 hashRate int32
mu sync.Mutex // protects dag mu sync.Mutex // protects dag
current *dag // current full DAG current *dag // current full DAG
@ -265,6 +266,7 @@ func (pow *Full) Search(block pow.Block, stop <-chan struct{}) (nonce uint64, mi
i := int64(0) i := int64(0)
starti := i starti := i
start := time.Now().UnixNano() start := time.Now().UnixNano()
previousHashrate := int32(0)
nonce = uint64(r.Int63()) nonce = uint64(r.Int63())
hash := hashToH256(block.HashNoNonce()) hash := hashToH256(block.HashNoNonce())
@ -272,14 +274,20 @@ func (pow *Full) Search(block pow.Block, stop <-chan struct{}) (nonce uint64, mi
for { for {
select { select {
case <-stop: case <-stop:
pow.hashRate = 0 atomic.AddInt32(&pow.hashRate, -previousHashrate)
return 0, nil return 0, nil
default: default:
i++ i++
// we don't have to update hash rate on every nonce, so update after
// first nonce check and then after 2^X nonces
if i == 2 || ((i % (1 << 16)) == 0) {
elapsed := time.Now().UnixNano() - start elapsed := time.Now().UnixNano() - start
hashes := ((float64(1e9) / float64(elapsed)) * float64(i-starti)) / 1000 hashes := (float64(1e9) / float64(elapsed)) * float64(i-starti)
pow.hashRate = int64(hashes) hashrateDiff := int32(hashes) - previousHashrate
previousHashrate = int32(hashes)
atomic.AddInt32(&pow.hashRate, hashrateDiff)
}
ret := C.ethash_full_compute(dag.ptr, hash, C.uint64_t(nonce)) ret := C.ethash_full_compute(dag.ptr, hash, C.uint64_t(nonce))
result := h256ToHash(ret.result).Big() result := h256ToHash(ret.result).Big()
@ -287,6 +295,7 @@ func (pow *Full) Search(block pow.Block, stop <-chan struct{}) (nonce uint64, mi
// TODO: disagrees with the spec https://github.com/ethereum/wiki/wiki/Ethash#mining // TODO: disagrees with the spec https://github.com/ethereum/wiki/wiki/Ethash#mining
if ret.success && result.Cmp(target) <= 0 { if ret.success && result.Cmp(target) <= 0 {
mixDigest = C.GoBytes(unsafe.Pointer(&ret.mix_hash), C.int(32)) mixDigest = C.GoBytes(unsafe.Pointer(&ret.mix_hash), C.int(32))
atomic.AddInt32(&pow.hashRate, -previousHashrate)
return nonce, mixDigest return nonce, mixDigest
} }
nonce += 1 nonce += 1
@ -299,8 +308,7 @@ func (pow *Full) Search(block pow.Block, stop <-chan struct{}) (nonce uint64, mi
} }
func (pow *Full) GetHashrate() int64 { func (pow *Full) GetHashrate() int64 {
// TODO: this needs to use an atomic operation. return int64(atomic.LoadInt32(&pow.hashRate))
return pow.hashRate
} }
func (pow *Full) Turbo(on bool) { func (pow *Full) Turbo(on bool) {

View File

@ -4,6 +4,7 @@
#include <stdlib.h> #include <stdlib.h>
#include <time.h> #include <time.h>
#include "../libethash/ethash.h" #include "../libethash/ethash.h"
#include "../libethash/internal.h"
#if PY_MAJOR_VERSION >= 3 #if PY_MAJOR_VERSION >= 3
#define PY_STRING_FORMAT "y#" #define PY_STRING_FORMAT "y#"
@ -15,67 +16,21 @@
#define MIX_WORDS (ETHASH_MIX_BYTES/4) #define MIX_WORDS (ETHASH_MIX_BYTES/4)
static PyObject *
get_cache_size(PyObject *self, PyObject *args) {
unsigned long block_number;
if (!PyArg_ParseTuple(args, "k", &block_number))
return 0;
if (block_number >= ETHASH_EPOCH_LENGTH * 2048) {
char error_message[1024];
sprintf(error_message, "Block number must be less than %i (was %lu)", ETHASH_EPOCH_LENGTH * 2048, block_number);
PyErr_SetString(PyExc_ValueError, error_message);
return 0;
}
return Py_BuildValue("i", ethash_get_cachesize(block_number));
}
static PyObject *
get_full_size(PyObject *self, PyObject *args) {
unsigned long block_number;
if (!PyArg_ParseTuple(args, "k", &block_number))
return 0;
if (block_number >= ETHASH_EPOCH_LENGTH * 2048) {
char error_message[1024];
sprintf(error_message, "Block number must be less than %i (was %lu)", ETHASH_EPOCH_LENGTH * 2048, block_number);
PyErr_SetString(PyExc_ValueError, error_message);
return 0;
}
return Py_BuildValue("i", ethash_get_datasize(block_number));
}
static PyObject * static PyObject *
mkcache_bytes(PyObject *self, PyObject *args) { mkcache_bytes(PyObject *self, PyObject *args) {
char *seed; unsigned long block_number;
unsigned long cache_size; unsigned long cache_size;
int seed_len;
if (!PyArg_ParseTuple(args, "k" PY_STRING_FORMAT, &cache_size, &seed, &seed_len)) if (!PyArg_ParseTuple(args, "k", &block_number))
return 0; return 0;
if (seed_len != 32) { ethash_light_t L = ethash_light_new(block_number);
char error_message[1024]; PyObject * val = Py_BuildValue(PY_STRING_FORMAT, L->cache, L->cache_size);
sprintf(error_message, "Seed must be 32 bytes long (was %i)", seed_len); free(L->cache);
PyErr_SetString(PyExc_ValueError, error_message);
return 0;
}
ethash_params params;
params.cache_size = (size_t) cache_size;
ethash_cache cache;
cache.mem = malloc(cache_size);
ethash_mkcache(&cache, &params, (ethash_h256_t *) seed);
PyObject * val = Py_BuildValue(PY_STRING_FORMAT, cache.mem, cache_size);
free(cache.mem);
return val; return val;
} }
/*
static PyObject * static PyObject *
calc_dataset_bytes(PyObject *self, PyObject *args) { calc_dataset_bytes(PyObject *self, PyObject *args) {
char *cache_bytes; char *cache_bytes;
@ -109,49 +64,38 @@ calc_dataset_bytes(PyObject *self, PyObject *args) {
PyObject * val = Py_BuildValue(PY_STRING_FORMAT, (char *) mem, full_size); PyObject * val = Py_BuildValue(PY_STRING_FORMAT, (char *) mem, full_size);
free(mem); free(mem);
return val; return val;
} }*/
// hashimoto_light(full_size, cache, header, nonce) // hashimoto_light(full_size, cache, header, nonce)
static PyObject * static PyObject *
hashimoto_light(PyObject *self, PyObject *args) { hashimoto_light(PyObject *self, PyObject *args) {
char *cache_bytes; char *cache_bytes;
char *header; char *header;
unsigned long full_size; unsigned long block_number;
unsigned long long nonce; unsigned long long nonce;
int cache_size, header_size; int cache_size, header_size;
if (!PyArg_ParseTuple(args, "k" PY_STRING_FORMAT PY_STRING_FORMAT "K", &full_size, &cache_bytes, &cache_size, &header, &header_size, &nonce)) if (!PyArg_ParseTuple(args, "k" PY_STRING_FORMAT PY_STRING_FORMAT "K", &block_number, &cache_bytes, &cache_size, &header, &header_size, &nonce))
return 0; return 0;
if (full_size % MIX_WORDS != 0) {
char error_message[1024];
sprintf(error_message, "The size of data set must be a multiple of %i bytes (was %lu)", MIX_WORDS, full_size);
PyErr_SetString(PyExc_ValueError, error_message);
return 0;
}
if (cache_size % ETHASH_HASH_BYTES != 0) {
char error_message[1024];
sprintf(error_message, "The size of the cache must be a multiple of %i bytes (was %i)", ETHASH_HASH_BYTES, cache_size);
PyErr_SetString(PyExc_ValueError, error_message);
return 0;
}
if (header_size != 32) { if (header_size != 32) {
char error_message[1024]; char error_message[1024];
sprintf(error_message, "Seed must be 32 bytes long (was %i)", header_size); sprintf(error_message, "Seed must be 32 bytes long (was %i)", header_size);
PyErr_SetString(PyExc_ValueError, error_message); PyErr_SetString(PyExc_ValueError, error_message);
return 0; return 0;
} }
struct ethash_light *s;
ethash_return_value out; s = calloc(sizeof(*s), 1);
ethash_params params; s->cache = cache_bytes;
params.cache_size = (size_t) cache_size; s->cache_size = cache_size;
params.full_size = (size_t) full_size; s->block_number = block_number;
ethash_cache cache; struct ethash_h256 *h;
cache.mem = (void *) cache_bytes; h = calloc(sizeof(*h), 1);
ethash_light(&out, &cache, &params, (ethash_h256_t *) header, nonce); for (int i = 0; i < 32; i++) h->b[i] = header[i];
struct ethash_return_value out = ethash_light_compute(s, *h, nonce);
return Py_BuildValue("{" PY_CONST_STRING_FORMAT ":" PY_STRING_FORMAT "," PY_CONST_STRING_FORMAT ":" PY_STRING_FORMAT "}", return Py_BuildValue("{" PY_CONST_STRING_FORMAT ":" PY_STRING_FORMAT "," PY_CONST_STRING_FORMAT ":" PY_STRING_FORMAT "}",
"mix digest", &out.mix_hash, 32, "mix digest", &out.mix_hash, 32,
"result", &out.result, 32); "result", &out.result, 32);
} }
/*
// hashimoto_full(dataset, header, nonce) // hashimoto_full(dataset, header, nonce)
static PyObject * static PyObject *
hashimoto_full(PyObject *self, PyObject *args) { hashimoto_full(PyObject *self, PyObject *args) {
@ -236,6 +180,7 @@ mine(PyObject *self, PyObject *args) {
"result", &out.result, 32, "result", &out.result, 32,
"nonce", nonce); "nonce", nonce);
} }
*/
//get_seedhash(block_number) //get_seedhash(block_number)
static PyObject * static PyObject *
@ -256,40 +201,24 @@ get_seedhash(PyObject *self, PyObject *args) {
static PyMethodDef PyethashMethods[] = static PyMethodDef PyethashMethods[] =
{ {
{"get_cache_size", get_cache_size, METH_VARARGS,
"get_cache_size(block_number)\n\n"
"Get the cache size for a given block number\n"
"\nExample:\n"
">>> get_cache_size(0)\n"
"1048384"},
{"get_full_size", get_full_size, METH_VARARGS,
"get_full_size(block_number)\n\n"
"Get the full size for a given block number\n"
"\nExample:\n"
">>> get_full_size(0)\n"
"1073739904"
},
{"get_seedhash", get_seedhash, METH_VARARGS, {"get_seedhash", get_seedhash, METH_VARARGS,
"get_seedhash(block_number)\n\n" "get_seedhash(block_number)\n\n"
"Gets the seedhash for a block."}, "Gets the seedhash for a block."},
{"mkcache_bytes", mkcache_bytes, METH_VARARGS, {"mkcache_bytes", mkcache_bytes, METH_VARARGS,
"mkcache_bytes(size, header)\n\n" "mkcache_bytes(block_number)\n\n"
"Makes a byte array for the cache for given cache size and seed hash\n" "Makes a byte array for the cache for given block number\n"},
"\nExample:\n" /*{"calc_dataset_bytes", calc_dataset_bytes, METH_VARARGS,
">>> pyethash.mkcache_bytes( 1024, \"~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~\").encode('hex')"
"\"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\""},
{"calc_dataset_bytes", calc_dataset_bytes, METH_VARARGS,
"calc_dataset_bytes(full_size, cache_bytes)\n\n" "calc_dataset_bytes(full_size, cache_bytes)\n\n"
"Makes a byte array for the dataset for a given size given cache bytes"}, "Makes a byte array for the dataset for a given size given cache bytes"},*/
{"hashimoto_light", hashimoto_light, METH_VARARGS, {"hashimoto_light", hashimoto_light, METH_VARARGS,
"hashimoto_light(full_size, cache_bytes, header, nonce)\n\n" "hashimoto_light(block_number, cache_bytes, header, nonce)\n\n"
"Runs the hashimoto hashing function just using cache bytes. Takes an int (full_size), byte array (cache_bytes), another byte array (header), and an int (nonce). Returns an object containing the mix digest, and hash result."}, "Runs the hashimoto hashing function just using cache bytes. Takes an int (full_size), byte array (cache_bytes), another byte array (header), and an int (nonce). Returns an object containing the mix digest, and hash result."},
{"hashimoto_full", hashimoto_full, METH_VARARGS, /*{"hashimoto_full", hashimoto_full, METH_VARARGS,
"hashimoto_full(dataset_bytes, header, nonce)\n\n" "hashimoto_full(dataset_bytes, header, nonce)\n\n"
"Runs the hashimoto hashing function using the dataset bytes. Useful for testing. Returns an object containing the mix digest (byte array), and hash result (another byte array)."}, "Runs the hashimoto hashing function using the dataset bytes. Useful for testing. Returns an object containing the mix digest (byte array), and hash result (another byte array)."},
{"mine", mine, METH_VARARGS, {"mine", mine, METH_VARARGS,
"mine(dataset_bytes, header, difficulty_bytes)\n\n" "mine(dataset_bytes, header, difficulty_bytes)\n\n"
"Mine for an adequate header. Returns an object containing the mix digest (byte array), hash result (another byte array) and nonce (an int)."}, "Mine for an adequate header. Returns an object containing the mix digest (byte array), hash result (another byte array) and nonce (an int)."},*/
{NULL, NULL, 0, NULL} {NULL, NULL, 0, NULL}
}; };

View File

@ -20,6 +20,8 @@ import (
"net/http" "net/http"
"net/url" "net/url"
"golang.org/x/net/html/charset"
"github.com/huin/goupnp/httpu" "github.com/huin/goupnp/httpu"
"github.com/huin/goupnp/ssdp" "github.com/huin/goupnp/ssdp"
) )
@ -104,6 +106,7 @@ func requestXml(url string, defaultSpace string, doc interface{}) error {
decoder := xml.NewDecoder(resp.Body) decoder := xml.NewDecoder(resp.Body)
decoder.DefaultSpace = defaultSpace decoder.DefaultSpace = defaultSpace
decoder.CharsetReader = charset.NewReaderLabel
return decoder.Decode(doc) return decoder.Decode(doc)
} }

View File

@ -0,0 +1,78 @@
// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Package atom provides integer codes (also known as atoms) for a fixed set of
// frequently occurring HTML strings: tag names and attribute keys such as "p"
// and "id".
//
// Sharing an atom's name between all elements with the same tag can result in
// fewer string allocations when tokenizing and parsing HTML. Integer
// comparisons are also generally faster than string comparisons.
//
// The value of an atom's particular code is not guaranteed to stay the same
// between versions of this package. Neither is any ordering guaranteed:
// whether atom.H1 < atom.H2 may also change. The codes are not guaranteed to
// be dense. The only guarantees are that e.g. looking up "div" will yield
// atom.Div, calling atom.Div.String will return "div", and atom.Div != 0.
package atom
// Atom is an integer code for a string. The zero value maps to "".
type Atom uint32
// String returns the atom's name.
func (a Atom) String() string {
start := uint32(a >> 8)
n := uint32(a & 0xff)
if start+n > uint32(len(atomText)) {
return ""
}
return atomText[start : start+n]
}
func (a Atom) string() string {
return atomText[a>>8 : a>>8+a&0xff]
}
// fnv computes the FNV hash with an arbitrary starting value h.
func fnv(h uint32, s []byte) uint32 {
for i := range s {
h ^= uint32(s[i])
h *= 16777619
}
return h
}
func match(s string, t []byte) bool {
for i, c := range t {
if s[i] != c {
return false
}
}
return true
}
// Lookup returns the atom whose name is s. It returns zero if there is no
// such atom. The lookup is case sensitive.
func Lookup(s []byte) Atom {
if len(s) == 0 || len(s) > maxAtomLen {
return 0
}
h := fnv(hash0, s)
if a := table[h&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
return a
}
if a := table[(h>>16)&uint32(len(table)-1)]; int(a&0xff) == len(s) && match(a.string(), s) {
return a
}
return 0
}
// String returns a string whose contents are equal to s. In that sense, it is
// equivalent to string(s) but may be more efficient.
func String(s []byte) string {
if a := Lookup(s); a != 0 {
return a.String()
}
return string(s)
}

View File

@ -0,0 +1,109 @@
// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package atom
import (
"sort"
"testing"
)
func TestKnown(t *testing.T) {
for _, s := range testAtomList {
if atom := Lookup([]byte(s)); atom.String() != s {
t.Errorf("Lookup(%q) = %#x (%q)", s, uint32(atom), atom.String())
}
}
}
func TestHits(t *testing.T) {
for _, a := range table {
if a == 0 {
continue
}
got := Lookup([]byte(a.String()))
if got != a {
t.Errorf("Lookup(%q) = %#x, want %#x", a.String(), uint32(got), uint32(a))
}
}
}
func TestMisses(t *testing.T) {
testCases := []string{
"",
"\x00",
"\xff",
"A",
"DIV",
"Div",
"dIV",
"aa",
"a\x00",
"ab",
"abb",
"abbr0",
"abbr ",
" abbr",
" a",
"acceptcharset",
"acceptCharset",
"accept_charset",
"h0",
"h1h2",
"h7",
"onClick",
"λ",
// The following string has the same hash (0xa1d7fab7) as "onmouseover".
"\x00\x00\x00\x00\x00\x50\x18\xae\x38\xd0\xb7",
}
for _, tc := range testCases {
got := Lookup([]byte(tc))
if got != 0 {
t.Errorf("Lookup(%q): got %d, want 0", tc, got)
}
}
}
func TestForeignObject(t *testing.T) {
const (
afo = Foreignobject
afO = ForeignObject
sfo = "foreignobject"
sfO = "foreignObject"
)
if got := Lookup([]byte(sfo)); got != afo {
t.Errorf("Lookup(%q): got %#v, want %#v", sfo, got, afo)
}
if got := Lookup([]byte(sfO)); got != afO {
t.Errorf("Lookup(%q): got %#v, want %#v", sfO, got, afO)
}
if got := afo.String(); got != sfo {
t.Errorf("Atom(%#v).String(): got %q, want %q", afo, got, sfo)
}
if got := afO.String(); got != sfO {
t.Errorf("Atom(%#v).String(): got %q, want %q", afO, got, sfO)
}
}
func BenchmarkLookup(b *testing.B) {
sortedTable := make([]string, 0, len(table))
for _, a := range table {
if a != 0 {
sortedTable = append(sortedTable, a.String())
}
}
sort.Strings(sortedTable)
x := make([][]byte, 1000)
for i := range x {
x[i] = []byte(sortedTable[i%len(sortedTable)])
}
b.ResetTimer()
for i := 0; i < b.N; i++ {
for _, s := range x {
Lookup(s)
}
}
}

648
Godeps/_workspace/src/golang.org/x/net/html/atom/gen.go generated vendored Normal file
View File

@ -0,0 +1,648 @@
// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// This program generates table.go and table_test.go.
// Invoke as
//
// go run gen.go |gofmt >table.go
// go run gen.go -test |gofmt >table_test.go
import (
"flag"
"fmt"
"math/rand"
"os"
"sort"
"strings"
)
// identifier converts s to a Go exported identifier.
// It converts "div" to "Div" and "accept-charset" to "AcceptCharset".
func identifier(s string) string {
b := make([]byte, 0, len(s))
cap := true
for _, c := range s {
if c == '-' {
cap = true
continue
}
if cap && 'a' <= c && c <= 'z' {
c -= 'a' - 'A'
}
cap = false
b = append(b, byte(c))
}
return string(b)
}
var test = flag.Bool("test", false, "generate table_test.go")
func main() {
flag.Parse()
var all []string
all = append(all, elements...)
all = append(all, attributes...)
all = append(all, eventHandlers...)
all = append(all, extra...)
sort.Strings(all)
if *test {
fmt.Printf("// generated by go run gen.go -test; DO NOT EDIT\n\n")
fmt.Printf("package atom\n\n")
fmt.Printf("var testAtomList = []string{\n")
for _, s := range all {
fmt.Printf("\t%q,\n", s)
}
fmt.Printf("}\n")
return
}
// uniq - lists have dups
// compute max len too
maxLen := 0
w := 0
for _, s := range all {
if w == 0 || all[w-1] != s {
if maxLen < len(s) {
maxLen = len(s)
}
all[w] = s
w++
}
}
all = all[:w]
// Find hash that minimizes table size.
var best *table
for i := 0; i < 1000000; i++ {
if best != nil && 1<<(best.k-1) < len(all) {
break
}
h := rand.Uint32()
for k := uint(0); k <= 16; k++ {
if best != nil && k >= best.k {
break
}
var t table
if t.init(h, k, all) {
best = &t
break
}
}
}
if best == nil {
fmt.Fprintf(os.Stderr, "failed to construct string table\n")
os.Exit(1)
}
// Lay out strings, using overlaps when possible.
layout := append([]string{}, all...)
// Remove strings that are substrings of other strings
for changed := true; changed; {
changed = false
for i, s := range layout {
if s == "" {
continue
}
for j, t := range layout {
if i != j && t != "" && strings.Contains(s, t) {
changed = true
layout[j] = ""
}
}
}
}
// Join strings where one suffix matches another prefix.
for {
// Find best i, j, k such that layout[i][len-k:] == layout[j][:k],
// maximizing overlap length k.
besti := -1
bestj := -1
bestk := 0
for i, s := range layout {
if s == "" {
continue
}
for j, t := range layout {
if i == j {
continue
}
for k := bestk + 1; k <= len(s) && k <= len(t); k++ {
if s[len(s)-k:] == t[:k] {
besti = i
bestj = j
bestk = k
}
}
}
}
if bestk > 0 {
layout[besti] += layout[bestj][bestk:]
layout[bestj] = ""
continue
}
break
}
text := strings.Join(layout, "")
atom := map[string]uint32{}
for _, s := range all {
off := strings.Index(text, s)
if off < 0 {
panic("lost string " + s)
}
atom[s] = uint32(off<<8 | len(s))
}
// Generate the Go code.
fmt.Printf("// generated by go run gen.go; DO NOT EDIT\n\n")
fmt.Printf("package atom\n\nconst (\n")
for _, s := range all {
fmt.Printf("\t%s Atom = %#x\n", identifier(s), atom[s])
}
fmt.Printf(")\n\n")
fmt.Printf("const hash0 = %#x\n\n", best.h0)
fmt.Printf("const maxAtomLen = %d\n\n", maxLen)
fmt.Printf("var table = [1<<%d]Atom{\n", best.k)
for i, s := range best.tab {
if s == "" {
continue
}
fmt.Printf("\t%#x: %#x, // %s\n", i, atom[s], s)
}
fmt.Printf("}\n")
datasize := (1 << best.k) * 4
fmt.Printf("const atomText =\n")
textsize := len(text)
for len(text) > 60 {
fmt.Printf("\t%q +\n", text[:60])
text = text[60:]
}
fmt.Printf("\t%q\n\n", text)
fmt.Fprintf(os.Stderr, "%d atoms; %d string bytes + %d tables = %d total data\n", len(all), textsize, datasize, textsize+datasize)
}
type byLen []string
func (x byLen) Less(i, j int) bool { return len(x[i]) > len(x[j]) }
func (x byLen) Swap(i, j int) { x[i], x[j] = x[j], x[i] }
func (x byLen) Len() int { return len(x) }
// fnv computes the FNV hash with an arbitrary starting value h.
func fnv(h uint32, s string) uint32 {
for i := 0; i < len(s); i++ {
h ^= uint32(s[i])
h *= 16777619
}
return h
}
// A table represents an attempt at constructing the lookup table.
// The lookup table uses cuckoo hashing, meaning that each string
// can be found in one of two positions.
type table struct {
h0 uint32
k uint
mask uint32
tab []string
}
// hash returns the two hashes for s.
func (t *table) hash(s string) (h1, h2 uint32) {
h := fnv(t.h0, s)
h1 = h & t.mask
h2 = (h >> 16) & t.mask
return
}
// init initializes the table with the given parameters.
// h0 is the initial hash value,
// k is the number of bits of hash value to use, and
// x is the list of strings to store in the table.
// init returns false if the table cannot be constructed.
func (t *table) init(h0 uint32, k uint, x []string) bool {
t.h0 = h0
t.k = k
t.tab = make([]string, 1<<k)
t.mask = 1<<k - 1
for _, s := range x {
if !t.insert(s) {
return false
}
}
return true
}
// insert inserts s in the table.
func (t *table) insert(s string) bool {
h1, h2 := t.hash(s)
if t.tab[h1] == "" {
t.tab[h1] = s
return true
}
if t.tab[h2] == "" {
t.tab[h2] = s
return true
}
if t.push(h1, 0) {
t.tab[h1] = s
return true
}
if t.push(h2, 0) {
t.tab[h2] = s
return true
}
return false
}
// push attempts to push aside the entry in slot i.
func (t *table) push(i uint32, depth int) bool {
if depth > len(t.tab) {
return false
}
s := t.tab[i]
h1, h2 := t.hash(s)
j := h1 + h2 - i
if t.tab[j] != "" && !t.push(j, depth+1) {
return false
}
t.tab[j] = s
return true
}
// The lists of element names and attribute keys were taken from
// https://html.spec.whatwg.org/multipage/indices.html#index
// as of the "HTML Living Standard - Last Updated 21 February 2015" version.
var elements = []string{
"a",
"abbr",
"address",
"area",
"article",
"aside",
"audio",
"b",
"base",
"bdi",
"bdo",
"blockquote",
"body",
"br",
"button",
"canvas",
"caption",
"cite",
"code",
"col",
"colgroup",
"command",
"data",
"datalist",
"dd",
"del",
"details",
"dfn",
"dialog",
"div",
"dl",
"dt",
"em",
"embed",
"fieldset",
"figcaption",
"figure",
"footer",
"form",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"header",
"hgroup",
"hr",
"html",
"i",
"iframe",
"img",
"input",
"ins",
"kbd",
"keygen",
"label",
"legend",
"li",
"link",
"map",
"mark",
"menu",
"menuitem",
"meta",
"meter",
"nav",
"noscript",
"object",
"ol",
"optgroup",
"option",
"output",
"p",
"param",
"pre",
"progress",
"q",
"rp",
"rt",
"ruby",
"s",
"samp",
"script",
"section",
"select",
"small",
"source",
"span",
"strong",
"style",
"sub",
"summary",
"sup",
"table",
"tbody",
"td",
"template",
"textarea",
"tfoot",
"th",
"thead",
"time",
"title",
"tr",
"track",
"u",
"ul",
"var",
"video",
"wbr",
}
// https://html.spec.whatwg.org/multipage/indices.html#attributes-3
var attributes = []string{
"abbr",
"accept",
"accept-charset",
"accesskey",
"action",
"alt",
"async",
"autocomplete",
"autofocus",
"autoplay",
"challenge",
"charset",
"checked",
"cite",
"class",
"cols",
"colspan",
"command",
"content",
"contenteditable",
"contextmenu",
"controls",
"coords",
"crossorigin",
"data",
"datetime",
"default",
"defer",
"dir",
"dirname",
"disabled",
"download",
"draggable",
"dropzone",
"enctype",
"for",
"form",
"formaction",
"formenctype",
"formmethod",
"formnovalidate",
"formtarget",
"headers",
"height",
"hidden",
"high",
"href",
"hreflang",
"http-equiv",
"icon",
"id",
"inputmode",
"ismap",
"itemid",
"itemprop",
"itemref",
"itemscope",
"itemtype",
"keytype",
"kind",
"label",
"lang",
"list",
"loop",
"low",
"manifest",
"max",
"maxlength",
"media",
"mediagroup",
"method",
"min",
"minlength",
"multiple",
"muted",
"name",
"novalidate",
"open",
"optimum",
"pattern",
"ping",
"placeholder",
"poster",
"preload",
"radiogroup",
"readonly",
"rel",
"required",
"reversed",
"rows",
"rowspan",
"sandbox",
"spellcheck",
"scope",
"scoped",
"seamless",
"selected",
"shape",
"size",
"sizes",
"sortable",
"sorted",
"span",
"src",
"srcdoc",
"srclang",
"start",
"step",
"style",
"tabindex",
"target",
"title",
"translate",
"type",
"typemustmatch",
"usemap",
"value",
"width",
"wrap",
}
var eventHandlers = []string{
"onabort",
"onautocomplete",
"onautocompleteerror",
"onafterprint",
"onbeforeprint",
"onbeforeunload",
"onblur",
"oncancel",
"oncanplay",
"oncanplaythrough",
"onchange",
"onclick",
"onclose",
"oncontextmenu",
"oncuechange",
"ondblclick",
"ondrag",
"ondragend",
"ondragenter",
"ondragleave",
"ondragover",
"ondragstart",
"ondrop",
"ondurationchange",
"onemptied",
"onended",
"onerror",
"onfocus",
"onhashchange",
"oninput",
"oninvalid",
"onkeydown",
"onkeypress",
"onkeyup",
"onlanguagechange",
"onload",
"onloadeddata",
"onloadedmetadata",
"onloadstart",
"onmessage",
"onmousedown",
"onmousemove",
"onmouseout",
"onmouseover",
"onmouseup",
"onmousewheel",
"onoffline",
"ononline",
"onpagehide",
"onpageshow",
"onpause",
"onplay",
"onplaying",
"onpopstate",
"onprogress",
"onratechange",
"onreset",
"onresize",
"onscroll",
"onseeked",
"onseeking",
"onselect",
"onshow",
"onsort",
"onstalled",
"onstorage",
"onsubmit",
"onsuspend",
"ontimeupdate",
"ontoggle",
"onunload",
"onvolumechange",
"onwaiting",
}
// extra are ad-hoc values not covered by any of the lists above.
var extra = []string{
"align",
"annotation",
"annotation-xml",
"applet",
"basefont",
"bgsound",
"big",
"blink",
"center",
"color",
"desc",
"face",
"font",
"foreignObject", // HTML is case-insensitive, but SVG-embedded-in-HTML is case-sensitive.
"foreignobject",
"frame",
"frameset",
"image",
"isindex",
"listing",
"malignmark",
"marquee",
"math",
"mglyph",
"mi",
"mn",
"mo",
"ms",
"mtext",
"nobr",
"noembed",
"noframes",
"plaintext",
"prompt",
"public",
"spacer",
"strike",
"svg",
"system",
"tt",
"xmp",
}

View File

@ -0,0 +1,713 @@
// generated by go run gen.go; DO NOT EDIT
package atom
const (
A Atom = 0x1
Abbr Atom = 0x4
Accept Atom = 0x2106
AcceptCharset Atom = 0x210e
Accesskey Atom = 0x3309
Action Atom = 0x1f606
Address Atom = 0x4f307
Align Atom = 0x1105
Alt Atom = 0x4503
Annotation Atom = 0x1670a
AnnotationXml Atom = 0x1670e
Applet Atom = 0x2b306
Area Atom = 0x2fa04
Article Atom = 0x38807
Aside Atom = 0x8305
Async Atom = 0x7b05
Audio Atom = 0xa605
Autocomplete Atom = 0x1fc0c
Autofocus Atom = 0xb309
Autoplay Atom = 0xce08
B Atom = 0x101
Base Atom = 0xd604
Basefont Atom = 0xd608
Bdi Atom = 0x1a03
Bdo Atom = 0xe703
Bgsound Atom = 0x11807
Big Atom = 0x12403
Blink Atom = 0x12705
Blockquote Atom = 0x12c0a
Body Atom = 0x2f04
Br Atom = 0x202
Button Atom = 0x13606
Canvas Atom = 0x7f06
Caption Atom = 0x1bb07
Center Atom = 0x5b506
Challenge Atom = 0x21f09
Charset Atom = 0x2807
Checked Atom = 0x32807
Cite Atom = 0x3c804
Class Atom = 0x4de05
Code Atom = 0x14904
Col Atom = 0x15003
Colgroup Atom = 0x15008
Color Atom = 0x15d05
Cols Atom = 0x16204
Colspan Atom = 0x16207
Command Atom = 0x17507
Content Atom = 0x42307
Contenteditable Atom = 0x4230f
Contextmenu Atom = 0x3310b
Controls Atom = 0x18808
Coords Atom = 0x19406
Crossorigin Atom = 0x19f0b
Data Atom = 0x44a04
Datalist Atom = 0x44a08
Datetime Atom = 0x23c08
Dd Atom = 0x26702
Default Atom = 0x8607
Defer Atom = 0x14b05
Del Atom = 0x3ef03
Desc Atom = 0x4db04
Details Atom = 0x4807
Dfn Atom = 0x6103
Dialog Atom = 0x1b06
Dir Atom = 0x6903
Dirname Atom = 0x6907
Disabled Atom = 0x10c08
Div Atom = 0x11303
Dl Atom = 0x11e02
Download Atom = 0x40008
Draggable Atom = 0x17b09
Dropzone Atom = 0x39108
Dt Atom = 0x50902
Em Atom = 0x6502
Embed Atom = 0x6505
Enctype Atom = 0x21107
Face Atom = 0x5b304
Fieldset Atom = 0x1b008
Figcaption Atom = 0x1b80a
Figure Atom = 0x1cc06
Font Atom = 0xda04
Footer Atom = 0x8d06
For Atom = 0x1d803
ForeignObject Atom = 0x1d80d
Foreignobject Atom = 0x1e50d
Form Atom = 0x1f204
Formaction Atom = 0x1f20a
Formenctype Atom = 0x20d0b
Formmethod Atom = 0x2280a
Formnovalidate Atom = 0x2320e
Formtarget Atom = 0x2470a
Frame Atom = 0x9a05
Frameset Atom = 0x9a08
H1 Atom = 0x26e02
H2 Atom = 0x29402
H3 Atom = 0x2a702
H4 Atom = 0x2e902
H5 Atom = 0x2f302
H6 Atom = 0x50b02
Head Atom = 0x2d504
Header Atom = 0x2d506
Headers Atom = 0x2d507
Height Atom = 0x25106
Hgroup Atom = 0x25906
Hidden Atom = 0x26506
High Atom = 0x26b04
Hr Atom = 0x27002
Href Atom = 0x27004
Hreflang Atom = 0x27008
Html Atom = 0x25504
HttpEquiv Atom = 0x2780a
I Atom = 0x601
Icon Atom = 0x42204
Id Atom = 0x8502
Iframe Atom = 0x29606
Image Atom = 0x29c05
Img Atom = 0x2a103
Input Atom = 0x3e805
Inputmode Atom = 0x3e809
Ins Atom = 0x1a803
Isindex Atom = 0x2a907
Ismap Atom = 0x2b005
Itemid Atom = 0x33c06
Itemprop Atom = 0x3c908
Itemref Atom = 0x5ad07
Itemscope Atom = 0x2b909
Itemtype Atom = 0x2c308
Kbd Atom = 0x1903
Keygen Atom = 0x3906
Keytype Atom = 0x53707
Kind Atom = 0x10904
Label Atom = 0xf005
Lang Atom = 0x27404
Legend Atom = 0x18206
Li Atom = 0x1202
Link Atom = 0x12804
List Atom = 0x44e04
Listing Atom = 0x44e07
Loop Atom = 0xf404
Low Atom = 0x11f03
Malignmark Atom = 0x100a
Manifest Atom = 0x5f108
Map Atom = 0x2b203
Mark Atom = 0x1604
Marquee Atom = 0x2cb07
Math Atom = 0x2d204
Max Atom = 0x2e103
Maxlength Atom = 0x2e109
Media Atom = 0x6e05
Mediagroup Atom = 0x6e0a
Menu Atom = 0x33804
Menuitem Atom = 0x33808
Meta Atom = 0x45d04
Meter Atom = 0x24205
Method Atom = 0x22c06
Mglyph Atom = 0x2a206
Mi Atom = 0x2eb02
Min Atom = 0x2eb03
Minlength Atom = 0x2eb09
Mn Atom = 0x23502
Mo Atom = 0x3ed02
Ms Atom = 0x2bc02
Mtext Atom = 0x2f505
Multiple Atom = 0x30308
Muted Atom = 0x30b05
Name Atom = 0x6c04
Nav Atom = 0x3e03
Nobr Atom = 0x5704
Noembed Atom = 0x6307
Noframes Atom = 0x9808
Noscript Atom = 0x3d208
Novalidate Atom = 0x2360a
Object Atom = 0x1ec06
Ol Atom = 0xc902
Onabort Atom = 0x13a07
Onafterprint Atom = 0x1c00c
Onautocomplete Atom = 0x1fa0e
Onautocompleteerror Atom = 0x1fa13
Onbeforeprint Atom = 0x6040d
Onbeforeunload Atom = 0x4e70e
Onblur Atom = 0xaa06
Oncancel Atom = 0xe908
Oncanplay Atom = 0x28509
Oncanplaythrough Atom = 0x28510
Onchange Atom = 0x3a708
Onclick Atom = 0x31007
Onclose Atom = 0x31707
Oncontextmenu Atom = 0x32f0d
Oncuechange Atom = 0x3420b
Ondblclick Atom = 0x34d0a
Ondrag Atom = 0x35706
Ondragend Atom = 0x35709
Ondragenter Atom = 0x3600b
Ondragleave Atom = 0x36b0b
Ondragover Atom = 0x3760a
Ondragstart Atom = 0x3800b
Ondrop Atom = 0x38f06
Ondurationchange Atom = 0x39f10
Onemptied Atom = 0x39609
Onended Atom = 0x3af07
Onerror Atom = 0x3b607
Onfocus Atom = 0x3bd07
Onhashchange Atom = 0x3da0c
Oninput Atom = 0x3e607
Oninvalid Atom = 0x3f209
Onkeydown Atom = 0x3fb09
Onkeypress Atom = 0x4080a
Onkeyup Atom = 0x41807
Onlanguagechange Atom = 0x43210
Onload Atom = 0x44206
Onloadeddata Atom = 0x4420c
Onloadedmetadata Atom = 0x45510
Onloadstart Atom = 0x46b0b
Onmessage Atom = 0x47609
Onmousedown Atom = 0x47f0b
Onmousemove Atom = 0x48a0b
Onmouseout Atom = 0x4950a
Onmouseover Atom = 0x4a20b
Onmouseup Atom = 0x4ad09
Onmousewheel Atom = 0x4b60c
Onoffline Atom = 0x4c209
Ononline Atom = 0x4cb08
Onpagehide Atom = 0x4d30a
Onpageshow Atom = 0x4fe0a
Onpause Atom = 0x50d07
Onplay Atom = 0x51706
Onplaying Atom = 0x51709
Onpopstate Atom = 0x5200a
Onprogress Atom = 0x52a0a
Onratechange Atom = 0x53e0c
Onreset Atom = 0x54a07
Onresize Atom = 0x55108
Onscroll Atom = 0x55f08
Onseeked Atom = 0x56708
Onseeking Atom = 0x56f09
Onselect Atom = 0x57808
Onshow Atom = 0x58206
Onsort Atom = 0x58b06
Onstalled Atom = 0x59509
Onstorage Atom = 0x59e09
Onsubmit Atom = 0x5a708
Onsuspend Atom = 0x5bb09
Ontimeupdate Atom = 0xdb0c
Ontoggle Atom = 0x5c408
Onunload Atom = 0x5cc08
Onvolumechange Atom = 0x5d40e
Onwaiting Atom = 0x5e209
Open Atom = 0x3cf04
Optgroup Atom = 0xf608
Optimum Atom = 0x5eb07
Option Atom = 0x60006
Output Atom = 0x49c06
P Atom = 0xc01
Param Atom = 0xc05
Pattern Atom = 0x5107
Ping Atom = 0x7704
Placeholder Atom = 0xc30b
Plaintext Atom = 0xfd09
Poster Atom = 0x15706
Pre Atom = 0x25e03
Preload Atom = 0x25e07
Progress Atom = 0x52c08
Prompt Atom = 0x5fa06
Public Atom = 0x41e06
Q Atom = 0x13101
Radiogroup Atom = 0x30a
Readonly Atom = 0x2fb08
Rel Atom = 0x25f03
Required Atom = 0x1d008
Reversed Atom = 0x5a08
Rows Atom = 0x9204
Rowspan Atom = 0x9207
Rp Atom = 0x1c602
Rt Atom = 0x13f02
Ruby Atom = 0xaf04
S Atom = 0x2c01
Samp Atom = 0x4e04
Sandbox Atom = 0xbb07
Scope Atom = 0x2bd05
Scoped Atom = 0x2bd06
Script Atom = 0x3d406
Seamless Atom = 0x31c08
Section Atom = 0x4e207
Select Atom = 0x57a06
Selected Atom = 0x57a08
Shape Atom = 0x4f905
Size Atom = 0x55504
Sizes Atom = 0x55505
Small Atom = 0x18f05
Sortable Atom = 0x58d08
Sorted Atom = 0x19906
Source Atom = 0x1aa06
Spacer Atom = 0x2db06
Span Atom = 0x9504
Spellcheck Atom = 0x3230a
Src Atom = 0x3c303
Srcdoc Atom = 0x3c306
Srclang Atom = 0x41107
Start Atom = 0x38605
Step Atom = 0x5f704
Strike Atom = 0x53306
Strong Atom = 0x55906
Style Atom = 0x61105
Sub Atom = 0x5a903
Summary Atom = 0x61607
Sup Atom = 0x61d03
Svg Atom = 0x62003
System Atom = 0x62306
Tabindex Atom = 0x46308
Table Atom = 0x42d05
Target Atom = 0x24b06
Tbody Atom = 0x2e05
Td Atom = 0x4702
Template Atom = 0x62608
Textarea Atom = 0x2f608
Tfoot Atom = 0x8c05
Th Atom = 0x22e02
Thead Atom = 0x2d405
Time Atom = 0xdd04
Title Atom = 0xa105
Tr Atom = 0x10502
Track Atom = 0x10505
Translate Atom = 0x14009
Tt Atom = 0x5302
Type Atom = 0x21404
Typemustmatch Atom = 0x2140d
U Atom = 0xb01
Ul Atom = 0x8a02
Usemap Atom = 0x51106
Value Atom = 0x4005
Var Atom = 0x11503
Video Atom = 0x28105
Wbr Atom = 0x12103
Width Atom = 0x50705
Wrap Atom = 0x58704
Xmp Atom = 0xc103
)
const hash0 = 0xc17da63e
const maxAtomLen = 19
var table = [1 << 9]Atom{
0x1: 0x48a0b, // onmousemove
0x2: 0x5e209, // onwaiting
0x3: 0x1fa13, // onautocompleteerror
0x4: 0x5fa06, // prompt
0x7: 0x5eb07, // optimum
0x8: 0x1604, // mark
0xa: 0x5ad07, // itemref
0xb: 0x4fe0a, // onpageshow
0xc: 0x57a06, // select
0xd: 0x17b09, // draggable
0xe: 0x3e03, // nav
0xf: 0x17507, // command
0x11: 0xb01, // u
0x14: 0x2d507, // headers
0x15: 0x44a08, // datalist
0x17: 0x4e04, // samp
0x1a: 0x3fb09, // onkeydown
0x1b: 0x55f08, // onscroll
0x1c: 0x15003, // col
0x20: 0x3c908, // itemprop
0x21: 0x2780a, // http-equiv
0x22: 0x61d03, // sup
0x24: 0x1d008, // required
0x2b: 0x25e07, // preload
0x2c: 0x6040d, // onbeforeprint
0x2d: 0x3600b, // ondragenter
0x2e: 0x50902, // dt
0x2f: 0x5a708, // onsubmit
0x30: 0x27002, // hr
0x31: 0x32f0d, // oncontextmenu
0x33: 0x29c05, // image
0x34: 0x50d07, // onpause
0x35: 0x25906, // hgroup
0x36: 0x7704, // ping
0x37: 0x57808, // onselect
0x3a: 0x11303, // div
0x3b: 0x1fa0e, // onautocomplete
0x40: 0x2eb02, // mi
0x41: 0x31c08, // seamless
0x42: 0x2807, // charset
0x43: 0x8502, // id
0x44: 0x5200a, // onpopstate
0x45: 0x3ef03, // del
0x46: 0x2cb07, // marquee
0x47: 0x3309, // accesskey
0x49: 0x8d06, // footer
0x4a: 0x44e04, // list
0x4b: 0x2b005, // ismap
0x51: 0x33804, // menu
0x52: 0x2f04, // body
0x55: 0x9a08, // frameset
0x56: 0x54a07, // onreset
0x57: 0x12705, // blink
0x58: 0xa105, // title
0x59: 0x38807, // article
0x5b: 0x22e02, // th
0x5d: 0x13101, // q
0x5e: 0x3cf04, // open
0x5f: 0x2fa04, // area
0x61: 0x44206, // onload
0x62: 0xda04, // font
0x63: 0xd604, // base
0x64: 0x16207, // colspan
0x65: 0x53707, // keytype
0x66: 0x11e02, // dl
0x68: 0x1b008, // fieldset
0x6a: 0x2eb03, // min
0x6b: 0x11503, // var
0x6f: 0x2d506, // header
0x70: 0x13f02, // rt
0x71: 0x15008, // colgroup
0x72: 0x23502, // mn
0x74: 0x13a07, // onabort
0x75: 0x3906, // keygen
0x76: 0x4c209, // onoffline
0x77: 0x21f09, // challenge
0x78: 0x2b203, // map
0x7a: 0x2e902, // h4
0x7b: 0x3b607, // onerror
0x7c: 0x2e109, // maxlength
0x7d: 0x2f505, // mtext
0x7e: 0xbb07, // sandbox
0x7f: 0x58b06, // onsort
0x80: 0x100a, // malignmark
0x81: 0x45d04, // meta
0x82: 0x7b05, // async
0x83: 0x2a702, // h3
0x84: 0x26702, // dd
0x85: 0x27004, // href
0x86: 0x6e0a, // mediagroup
0x87: 0x19406, // coords
0x88: 0x41107, // srclang
0x89: 0x34d0a, // ondblclick
0x8a: 0x4005, // value
0x8c: 0xe908, // oncancel
0x8e: 0x3230a, // spellcheck
0x8f: 0x9a05, // frame
0x91: 0x12403, // big
0x94: 0x1f606, // action
0x95: 0x6903, // dir
0x97: 0x2fb08, // readonly
0x99: 0x42d05, // table
0x9a: 0x61607, // summary
0x9b: 0x12103, // wbr
0x9c: 0x30a, // radiogroup
0x9d: 0x6c04, // name
0x9f: 0x62306, // system
0xa1: 0x15d05, // color
0xa2: 0x7f06, // canvas
0xa3: 0x25504, // html
0xa5: 0x56f09, // onseeking
0xac: 0x4f905, // shape
0xad: 0x25f03, // rel
0xae: 0x28510, // oncanplaythrough
0xaf: 0x3760a, // ondragover
0xb0: 0x62608, // template
0xb1: 0x1d80d, // foreignObject
0xb3: 0x9204, // rows
0xb6: 0x44e07, // listing
0xb7: 0x49c06, // output
0xb9: 0x3310b, // contextmenu
0xbb: 0x11f03, // low
0xbc: 0x1c602, // rp
0xbd: 0x5bb09, // onsuspend
0xbe: 0x13606, // button
0xbf: 0x4db04, // desc
0xc1: 0x4e207, // section
0xc2: 0x52a0a, // onprogress
0xc3: 0x59e09, // onstorage
0xc4: 0x2d204, // math
0xc5: 0x4503, // alt
0xc7: 0x8a02, // ul
0xc8: 0x5107, // pattern
0xc9: 0x4b60c, // onmousewheel
0xca: 0x35709, // ondragend
0xcb: 0xaf04, // ruby
0xcc: 0xc01, // p
0xcd: 0x31707, // onclose
0xce: 0x24205, // meter
0xcf: 0x11807, // bgsound
0xd2: 0x25106, // height
0xd4: 0x101, // b
0xd5: 0x2c308, // itemtype
0xd8: 0x1bb07, // caption
0xd9: 0x10c08, // disabled
0xdb: 0x33808, // menuitem
0xdc: 0x62003, // svg
0xdd: 0x18f05, // small
0xde: 0x44a04, // data
0xe0: 0x4cb08, // ononline
0xe1: 0x2a206, // mglyph
0xe3: 0x6505, // embed
0xe4: 0x10502, // tr
0xe5: 0x46b0b, // onloadstart
0xe7: 0x3c306, // srcdoc
0xeb: 0x5c408, // ontoggle
0xed: 0xe703, // bdo
0xee: 0x4702, // td
0xef: 0x8305, // aside
0xf0: 0x29402, // h2
0xf1: 0x52c08, // progress
0xf2: 0x12c0a, // blockquote
0xf4: 0xf005, // label
0xf5: 0x601, // i
0xf7: 0x9207, // rowspan
0xfb: 0x51709, // onplaying
0xfd: 0x2a103, // img
0xfe: 0xf608, // optgroup
0xff: 0x42307, // content
0x101: 0x53e0c, // onratechange
0x103: 0x3da0c, // onhashchange
0x104: 0x4807, // details
0x106: 0x40008, // download
0x109: 0x14009, // translate
0x10b: 0x4230f, // contenteditable
0x10d: 0x36b0b, // ondragleave
0x10e: 0x2106, // accept
0x10f: 0x57a08, // selected
0x112: 0x1f20a, // formaction
0x113: 0x5b506, // center
0x115: 0x45510, // onloadedmetadata
0x116: 0x12804, // link
0x117: 0xdd04, // time
0x118: 0x19f0b, // crossorigin
0x119: 0x3bd07, // onfocus
0x11a: 0x58704, // wrap
0x11b: 0x42204, // icon
0x11d: 0x28105, // video
0x11e: 0x4de05, // class
0x121: 0x5d40e, // onvolumechange
0x122: 0xaa06, // onblur
0x123: 0x2b909, // itemscope
0x124: 0x61105, // style
0x127: 0x41e06, // public
0x129: 0x2320e, // formnovalidate
0x12a: 0x58206, // onshow
0x12c: 0x51706, // onplay
0x12d: 0x3c804, // cite
0x12e: 0x2bc02, // ms
0x12f: 0xdb0c, // ontimeupdate
0x130: 0x10904, // kind
0x131: 0x2470a, // formtarget
0x135: 0x3af07, // onended
0x136: 0x26506, // hidden
0x137: 0x2c01, // s
0x139: 0x2280a, // formmethod
0x13a: 0x3e805, // input
0x13c: 0x50b02, // h6
0x13d: 0xc902, // ol
0x13e: 0x3420b, // oncuechange
0x13f: 0x1e50d, // foreignobject
0x143: 0x4e70e, // onbeforeunload
0x144: 0x2bd05, // scope
0x145: 0x39609, // onemptied
0x146: 0x14b05, // defer
0x147: 0xc103, // xmp
0x148: 0x39f10, // ondurationchange
0x149: 0x1903, // kbd
0x14c: 0x47609, // onmessage
0x14d: 0x60006, // option
0x14e: 0x2eb09, // minlength
0x14f: 0x32807, // checked
0x150: 0xce08, // autoplay
0x152: 0x202, // br
0x153: 0x2360a, // novalidate
0x156: 0x6307, // noembed
0x159: 0x31007, // onclick
0x15a: 0x47f0b, // onmousedown
0x15b: 0x3a708, // onchange
0x15e: 0x3f209, // oninvalid
0x15f: 0x2bd06, // scoped
0x160: 0x18808, // controls
0x161: 0x30b05, // muted
0x162: 0x58d08, // sortable
0x163: 0x51106, // usemap
0x164: 0x1b80a, // figcaption
0x165: 0x35706, // ondrag
0x166: 0x26b04, // high
0x168: 0x3c303, // src
0x169: 0x15706, // poster
0x16b: 0x1670e, // annotation-xml
0x16c: 0x5f704, // step
0x16d: 0x4, // abbr
0x16e: 0x1b06, // dialog
0x170: 0x1202, // li
0x172: 0x3ed02, // mo
0x175: 0x1d803, // for
0x176: 0x1a803, // ins
0x178: 0x55504, // size
0x179: 0x43210, // onlanguagechange
0x17a: 0x8607, // default
0x17b: 0x1a03, // bdi
0x17c: 0x4d30a, // onpagehide
0x17d: 0x6907, // dirname
0x17e: 0x21404, // type
0x17f: 0x1f204, // form
0x181: 0x28509, // oncanplay
0x182: 0x6103, // dfn
0x183: 0x46308, // tabindex
0x186: 0x6502, // em
0x187: 0x27404, // lang
0x189: 0x39108, // dropzone
0x18a: 0x4080a, // onkeypress
0x18b: 0x23c08, // datetime
0x18c: 0x16204, // cols
0x18d: 0x1, // a
0x18e: 0x4420c, // onloadeddata
0x190: 0xa605, // audio
0x192: 0x2e05, // tbody
0x193: 0x22c06, // method
0x195: 0xf404, // loop
0x196: 0x29606, // iframe
0x198: 0x2d504, // head
0x19e: 0x5f108, // manifest
0x19f: 0xb309, // autofocus
0x1a0: 0x14904, // code
0x1a1: 0x55906, // strong
0x1a2: 0x30308, // multiple
0x1a3: 0xc05, // param
0x1a6: 0x21107, // enctype
0x1a7: 0x5b304, // face
0x1a8: 0xfd09, // plaintext
0x1a9: 0x26e02, // h1
0x1aa: 0x59509, // onstalled
0x1ad: 0x3d406, // script
0x1ae: 0x2db06, // spacer
0x1af: 0x55108, // onresize
0x1b0: 0x4a20b, // onmouseover
0x1b1: 0x5cc08, // onunload
0x1b2: 0x56708, // onseeked
0x1b4: 0x2140d, // typemustmatch
0x1b5: 0x1cc06, // figure
0x1b6: 0x4950a, // onmouseout
0x1b7: 0x25e03, // pre
0x1b8: 0x50705, // width
0x1b9: 0x19906, // sorted
0x1bb: 0x5704, // nobr
0x1be: 0x5302, // tt
0x1bf: 0x1105, // align
0x1c0: 0x3e607, // oninput
0x1c3: 0x41807, // onkeyup
0x1c6: 0x1c00c, // onafterprint
0x1c7: 0x210e, // accept-charset
0x1c8: 0x33c06, // itemid
0x1c9: 0x3e809, // inputmode
0x1cb: 0x53306, // strike
0x1cc: 0x5a903, // sub
0x1cd: 0x10505, // track
0x1ce: 0x38605, // start
0x1d0: 0xd608, // basefont
0x1d6: 0x1aa06, // source
0x1d7: 0x18206, // legend
0x1d8: 0x2d405, // thead
0x1da: 0x8c05, // tfoot
0x1dd: 0x1ec06, // object
0x1de: 0x6e05, // media
0x1df: 0x1670a, // annotation
0x1e0: 0x20d0b, // formenctype
0x1e2: 0x3d208, // noscript
0x1e4: 0x55505, // sizes
0x1e5: 0x1fc0c, // autocomplete
0x1e6: 0x9504, // span
0x1e7: 0x9808, // noframes
0x1e8: 0x24b06, // target
0x1e9: 0x38f06, // ondrop
0x1ea: 0x2b306, // applet
0x1ec: 0x5a08, // reversed
0x1f0: 0x2a907, // isindex
0x1f3: 0x27008, // hreflang
0x1f5: 0x2f302, // h5
0x1f6: 0x4f307, // address
0x1fa: 0x2e103, // max
0x1fb: 0xc30b, // placeholder
0x1fc: 0x2f608, // textarea
0x1fe: 0x4ad09, // onmouseup
0x1ff: 0x3800b, // ondragstart
}
const atomText = "abbradiogrouparamalignmarkbdialogaccept-charsetbodyaccesskey" +
"genavaluealtdetailsampatternobreversedfnoembedirnamediagroup" +
"ingasyncanvasidefaultfooterowspanoframesetitleaudionblurubya" +
"utofocusandboxmplaceholderautoplaybasefontimeupdatebdoncance" +
"labelooptgrouplaintextrackindisabledivarbgsoundlowbrbigblink" +
"blockquotebuttonabortranslatecodefercolgroupostercolorcolspa" +
"nnotation-xmlcommandraggablegendcontrolsmallcoordsortedcross" +
"originsourcefieldsetfigcaptionafterprintfigurequiredforeignO" +
"bjectforeignobjectformactionautocompleteerrorformenctypemust" +
"matchallengeformmethodformnovalidatetimeterformtargetheightm" +
"lhgroupreloadhiddenhigh1hreflanghttp-equivideoncanplaythroug" +
"h2iframeimageimglyph3isindexismappletitemscopeditemtypemarqu" +
"eematheaderspacermaxlength4minlength5mtextareadonlymultiplem" +
"utedonclickoncloseamlesspellcheckedoncontextmenuitemidoncuec" +
"hangeondblclickondragendondragenterondragleaveondragoverondr" +
"agstarticleondropzonemptiedondurationchangeonendedonerroronf" +
"ocusrcdocitempropenoscriptonhashchangeoninputmodeloninvalido" +
"nkeydownloadonkeypressrclangonkeyupublicontenteditableonlang" +
"uagechangeonloadeddatalistingonloadedmetadatabindexonloadsta" +
"rtonmessageonmousedownonmousemoveonmouseoutputonmouseoveronm" +
"ouseuponmousewheelonofflineononlineonpagehidesclassectionbef" +
"oreunloaddresshapeonpageshowidth6onpausemaponplayingonpopsta" +
"teonprogresstrikeytypeonratechangeonresetonresizestrongonscr" +
"ollonseekedonseekingonselectedonshowraponsortableonstalledon" +
"storageonsubmitemrefacenteronsuspendontoggleonunloadonvolume" +
"changeonwaitingoptimumanifestepromptoptionbeforeprintstylesu" +
"mmarysupsvgsystemplate"

View File

@ -0,0 +1,351 @@
// generated by go run gen.go -test; DO NOT EDIT
package atom
var testAtomList = []string{
"a",
"abbr",
"abbr",
"accept",
"accept-charset",
"accesskey",
"action",
"address",
"align",
"alt",
"annotation",
"annotation-xml",
"applet",
"area",
"article",
"aside",
"async",
"audio",
"autocomplete",
"autofocus",
"autoplay",
"b",
"base",
"basefont",
"bdi",
"bdo",
"bgsound",
"big",
"blink",
"blockquote",
"body",
"br",
"button",
"canvas",
"caption",
"center",
"challenge",
"charset",
"checked",
"cite",
"cite",
"class",
"code",
"col",
"colgroup",
"color",
"cols",
"colspan",
"command",
"command",
"content",
"contenteditable",
"contextmenu",
"controls",
"coords",
"crossorigin",
"data",
"data",
"datalist",
"datetime",
"dd",
"default",
"defer",
"del",
"desc",
"details",
"dfn",
"dialog",
"dir",
"dirname",
"disabled",
"div",
"dl",
"download",
"draggable",
"dropzone",
"dt",
"em",
"embed",
"enctype",
"face",
"fieldset",
"figcaption",
"figure",
"font",
"footer",
"for",
"foreignObject",
"foreignobject",
"form",
"form",
"formaction",
"formenctype",
"formmethod",
"formnovalidate",
"formtarget",
"frame",
"frameset",
"h1",
"h2",
"h3",
"h4",
"h5",
"h6",
"head",
"header",
"headers",
"height",
"hgroup",
"hidden",
"high",
"hr",
"href",
"hreflang",
"html",
"http-equiv",
"i",
"icon",
"id",
"iframe",
"image",
"img",
"input",
"inputmode",
"ins",
"isindex",
"ismap",
"itemid",
"itemprop",
"itemref",
"itemscope",
"itemtype",
"kbd",
"keygen",
"keytype",
"kind",
"label",
"label",
"lang",
"legend",
"li",
"link",
"list",
"listing",
"loop",
"low",
"malignmark",
"manifest",
"map",
"mark",
"marquee",
"math",
"max",
"maxlength",
"media",
"mediagroup",
"menu",
"menuitem",
"meta",
"meter",
"method",
"mglyph",
"mi",
"min",
"minlength",
"mn",
"mo",
"ms",
"mtext",
"multiple",
"muted",
"name",
"nav",
"nobr",
"noembed",
"noframes",
"noscript",
"novalidate",
"object",
"ol",
"onabort",
"onafterprint",
"onautocomplete",
"onautocompleteerror",
"onbeforeprint",
"onbeforeunload",
"onblur",
"oncancel",
"oncanplay",
"oncanplaythrough",
"onchange",
"onclick",
"onclose",
"oncontextmenu",
"oncuechange",
"ondblclick",
"ondrag",
"ondragend",
"ondragenter",
"ondragleave",
"ondragover",
"ondragstart",
"ondrop",
"ondurationchange",
"onemptied",
"onended",
"onerror",
"onfocus",
"onhashchange",
"oninput",
"oninvalid",
"onkeydown",
"onkeypress",
"onkeyup",
"onlanguagechange",
"onload",
"onloadeddata",
"onloadedmetadata",
"onloadstart",
"onmessage",
"onmousedown",
"onmousemove",
"onmouseout",
"onmouseover",
"onmouseup",
"onmousewheel",
"onoffline",
"ononline",
"onpagehide",
"onpageshow",
"onpause",
"onplay",
"onplaying",
"onpopstate",
"onprogress",
"onratechange",
"onreset",
"onresize",
"onscroll",
"onseeked",
"onseeking",
"onselect",
"onshow",
"onsort",
"onstalled",
"onstorage",
"onsubmit",
"onsuspend",
"ontimeupdate",
"ontoggle",
"onunload",
"onvolumechange",
"onwaiting",
"open",
"optgroup",
"optimum",
"option",
"output",
"p",
"param",
"pattern",
"ping",
"placeholder",
"plaintext",
"poster",
"pre",
"preload",
"progress",
"prompt",
"public",
"q",
"radiogroup",
"readonly",
"rel",
"required",
"reversed",
"rows",
"rowspan",
"rp",
"rt",
"ruby",
"s",
"samp",
"sandbox",
"scope",
"scoped",
"script",
"seamless",
"section",
"select",
"selected",
"shape",
"size",
"sizes",
"small",
"sortable",
"sorted",
"source",
"spacer",
"span",
"span",
"spellcheck",
"src",
"srcdoc",
"srclang",
"start",
"step",
"strike",
"strong",
"style",
"style",
"sub",
"summary",
"sup",
"svg",
"system",
"tabindex",
"table",
"target",
"tbody",
"td",
"template",
"textarea",
"tfoot",
"th",
"thead",
"time",
"title",
"title",
"tr",
"track",
"translate",
"tt",
"type",
"typemustmatch",
"u",
"ul",
"usemap",
"value",
"var",
"video",
"wbr",
"width",
"wrap",
"xmp",
}

View File

@ -0,0 +1,244 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// Package charset provides common text encodings for HTML documents.
//
// The mapping from encoding labels to encodings is defined at
// https://encoding.spec.whatwg.org/.
package charset
import (
"bytes"
"fmt"
"io"
"mime"
"strings"
"unicode/utf8"
"golang.org/x/net/html"
"golang.org/x/text/encoding"
"golang.org/x/text/encoding/charmap"
"golang.org/x/text/transform"
)
// Lookup returns the encoding with the specified label, and its canonical
// name. It returns nil and the empty string if label is not one of the
// standard encodings for HTML. Matching is case-insensitive and ignores
// leading and trailing whitespace.
func Lookup(label string) (e encoding.Encoding, name string) {
label = strings.ToLower(strings.Trim(label, "\t\n\r\f "))
enc := encodings[label]
return enc.e, enc.name
}
// DetermineEncoding determines the encoding of an HTML document by examining
// up to the first 1024 bytes of content and the declared Content-Type.
//
// See http://www.whatwg.org/specs/web-apps/current-work/multipage/parsing.html#determining-the-character-encoding
func DetermineEncoding(content []byte, contentType string) (e encoding.Encoding, name string, certain bool) {
if len(content) > 1024 {
content = content[:1024]
}
for _, b := range boms {
if bytes.HasPrefix(content, b.bom) {
e, name = Lookup(b.enc)
return e, name, true
}
}
if _, params, err := mime.ParseMediaType(contentType); err == nil {
if cs, ok := params["charset"]; ok {
if e, name = Lookup(cs); e != nil {
return e, name, true
}
}
}
if len(content) > 0 {
e, name = prescan(content)
if e != nil {
return e, name, false
}
}
// Try to detect UTF-8.
// First eliminate any partial rune at the end.
for i := len(content) - 1; i >= 0 && i > len(content)-4; i-- {
b := content[i]
if b < 0x80 {
break
}
if utf8.RuneStart(b) {
content = content[:i]
break
}
}
hasHighBit := false
for _, c := range content {
if c >= 0x80 {
hasHighBit = true
break
}
}
if hasHighBit && utf8.Valid(content) {
return encoding.Nop, "utf-8", false
}
// TODO: change default depending on user's locale?
return charmap.Windows1252, "windows-1252", false
}
// NewReader returns an io.Reader that converts the content of r to UTF-8.
// It calls DetermineEncoding to find out what r's encoding is.
func NewReader(r io.Reader, contentType string) (io.Reader, error) {
preview := make([]byte, 1024)
n, err := io.ReadFull(r, preview)
switch {
case err == io.ErrUnexpectedEOF:
preview = preview[:n]
r = bytes.NewReader(preview)
case err != nil:
return nil, err
default:
r = io.MultiReader(bytes.NewReader(preview), r)
}
if e, _, _ := DetermineEncoding(preview, contentType); e != encoding.Nop {
r = transform.NewReader(r, e.NewDecoder())
}
return r, nil
}
// NewReaderLabel returns a reader that converts from the specified charset to
// UTF-8. It uses Lookup to find the encoding that corresponds to label, and
// returns an error if Lookup returns nil. It is suitable for use as
// encoding/xml.Decoder's CharsetReader function.
func NewReaderLabel(label string, input io.Reader) (io.Reader, error) {
e, _ := Lookup(label)
if e == nil {
return nil, fmt.Errorf("unsupported charset: %q", label)
}
return transform.NewReader(input, e.NewDecoder()), nil
}
func prescan(content []byte) (e encoding.Encoding, name string) {
z := html.NewTokenizer(bytes.NewReader(content))
for {
switch z.Next() {
case html.ErrorToken:
return nil, ""
case html.StartTagToken, html.SelfClosingTagToken:
tagName, hasAttr := z.TagName()
if !bytes.Equal(tagName, []byte("meta")) {
continue
}
attrList := make(map[string]bool)
gotPragma := false
const (
dontKnow = iota
doNeedPragma
doNotNeedPragma
)
needPragma := dontKnow
name = ""
e = nil
for hasAttr {
var key, val []byte
key, val, hasAttr = z.TagAttr()
ks := string(key)
if attrList[ks] {
continue
}
attrList[ks] = true
for i, c := range val {
if 'A' <= c && c <= 'Z' {
val[i] = c + 0x20
}
}
switch ks {
case "http-equiv":
if bytes.Equal(val, []byte("content-type")) {
gotPragma = true
}
case "content":
if e == nil {
name = fromMetaElement(string(val))
if name != "" {
e, name = Lookup(name)
if e != nil {
needPragma = doNeedPragma
}
}
}
case "charset":
e, name = Lookup(string(val))
needPragma = doNotNeedPragma
}
}
if needPragma == dontKnow || needPragma == doNeedPragma && !gotPragma {
continue
}
if strings.HasPrefix(name, "utf-16") {
name = "utf-8"
e = encoding.Nop
}
if e != nil {
return e, name
}
}
}
}
func fromMetaElement(s string) string {
for s != "" {
csLoc := strings.Index(s, "charset")
if csLoc == -1 {
return ""
}
s = s[csLoc+len("charset"):]
s = strings.TrimLeft(s, " \t\n\f\r")
if !strings.HasPrefix(s, "=") {
continue
}
s = s[1:]
s = strings.TrimLeft(s, " \t\n\f\r")
if s == "" {
return ""
}
if q := s[0]; q == '"' || q == '\'' {
s = s[1:]
closeQuote := strings.IndexRune(s, rune(q))
if closeQuote == -1 {
return ""
}
return s[:closeQuote]
}
end := strings.IndexAny(s, "; \t\n\f\r")
if end == -1 {
end = len(s)
}
return s[:end]
}
return ""
}
var boms = []struct {
bom []byte
enc string
}{
{[]byte{0xfe, 0xff}, "utf-16be"},
{[]byte{0xff, 0xfe}, "utf-16le"},
{[]byte{0xef, 0xbb, 0xbf}, "utf-8"},
}

View File

@ -0,0 +1,236 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package charset
import (
"bytes"
"encoding/xml"
"io/ioutil"
"runtime"
"strings"
"testing"
"golang.org/x/text/transform"
)
func transformString(t transform.Transformer, s string) (string, error) {
r := transform.NewReader(strings.NewReader(s), t)
b, err := ioutil.ReadAll(r)
return string(b), err
}
var testCases = []struct {
utf8, other, otherEncoding string
}{
{"Résumé", "Résumé", "utf8"},
{"Résumé", "R\xe9sum\xe9", "latin1"},
{"これは漢字です。", "S0\x8c0o0\"oW[g0Y0\x020", "UTF-16LE"},
{"これは漢字です。", "0S0\x8c0oo\"[W0g0Y0\x02", "UTF-16BE"},
{"Hello, world", "Hello, world", "ASCII"},
{"Gdańsk", "Gda\xf1sk", "ISO-8859-2"},
{"Ââ Čč Đđ Ŋŋ Õõ Šš Žž Åå Ää", "\xc2\xe2 \xc8\xe8 \xa9\xb9 \xaf\xbf \xd5\xf5 \xaa\xba \xac\xbc \xc5\xe5 \xc4\xe4", "ISO-8859-10"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "ISO-8859-11"},
{"latviešu", "latvie\xf0u", "ISO-8859-13"},
{"Seònaid", "Se\xf2naid", "ISO-8859-14"},
{"€1 is cheap", "\xa41 is cheap", "ISO-8859-15"},
{"românește", "rom\xe2ne\xbate", "ISO-8859-16"},
{"nutraĵo", "nutra\xbco", "ISO-8859-3"},
{"Kalâdlit", "Kal\xe2dlit", "ISO-8859-4"},
{"русский", "\xe0\xe3\xe1\xe1\xda\xd8\xd9", "ISO-8859-5"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "ISO-8859-7"},
{"Kağan", "Ka\xf0an", "ISO-8859-9"},
{"Résumé", "R\x8esum\x8e", "macintosh"},
{"Gdańsk", "Gda\xf1sk", "windows-1250"},
{"русский", "\xf0\xf3\xf1\xf1\xea\xe8\xe9", "windows-1251"},
{"Résumé", "R\xe9sum\xe9", "windows-1252"},
{"ελληνικά", "\xe5\xeb\xeb\xe7\xed\xe9\xea\xdc", "windows-1253"},
{"Kağan", "Ka\xf0an", "windows-1254"},
{"עִבְרִית", "\xf2\xc4\xe1\xc0\xf8\xc4\xe9\xfa", "windows-1255"},
{"العربية", "\xc7\xe1\xda\xd1\xc8\xed\xc9", "windows-1256"},
{"latviešu", "latvie\xf0u", "windows-1257"},
{"Việt", "Vi\xea\xf2t", "windows-1258"},
{"สำหรับ", "\xca\xd3\xcb\xc3\u047a", "windows-874"},
{"русский", "\xd2\xd5\xd3\xd3\xcb\xc9\xca", "KOI8-R"},
{"українська", "\xd5\xcb\xd2\xc1\xa7\xce\xd3\xd8\xcb\xc1", "KOI8-U"},
{"Hello 常用國字標準字體表", "Hello \xb1`\xa5\u03b0\xea\xa6r\xbc\u0437\u01e6r\xc5\xe9\xaa\xed", "big5"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gbk"},
{"Hello 常用國字標準字體表", "Hello \xb3\xa3\xd3\xc3\x87\xf8\xd7\xd6\x98\xcb\x9c\xca\xd7\xd6\xf3\x77\xb1\xed", "gb18030"},
{"עִבְרִית", "\x81\x30\xfb\x30\x81\x30\xf6\x34\x81\x30\xf9\x33\x81\x30\xf6\x30\x81\x30\xfb\x36\x81\x30\xf6\x34\x81\x30\xfa\x31\x81\x30\xfb\x38", "gb18030"},
{"㧯", "\x82\x31\x89\x38", "gb18030"},
{"これは漢字です。", "\x82\xb1\x82\xea\x82\xcd\x8a\xbf\x8e\x9a\x82\xc5\x82\xb7\x81B", "SJIS"},
{"Hello, 世界!", "Hello, \x90\xa2\x8aE!", "SJIS"},
{"イウエオカ", "\xb2\xb3\xb4\xb5\xb6", "SJIS"},
{"これは漢字です。", "\xa4\xb3\xa4\xec\xa4\u03f4\xc1\xbb\xfa\xa4\u01e4\xb9\xa1\xa3", "EUC-JP"},
{"Hello, 世界!", "Hello, \x1b$B@$3&\x1b(B!", "ISO-2022-JP"},
{"네이트 | 즐거움의 시작, 슈파스(Spaβ) NATE", "\xb3\xd7\xc0\xcc\xc6\xae | \xc1\xf1\xb0\xc5\xbf\xf2\xc0\xc7 \xbd\xc3\xc0\xdb, \xbd\xb4\xc6\xc4\xbd\xba(Spa\xa5\xe2) NATE", "EUC-KR"},
}
func TestDecode(t *testing.T) {
for _, tc := range testCases {
e, _ := Lookup(tc.otherEncoding)
if e == nil {
t.Errorf("%s: not found", tc.otherEncoding)
continue
}
s, err := transformString(e.NewDecoder(), tc.other)
if err != nil {
t.Errorf("%s: decode %q: %v", tc.otherEncoding, tc.other, err)
continue
}
if s != tc.utf8 {
t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.utf8)
}
}
}
func TestEncode(t *testing.T) {
for _, tc := range testCases {
e, _ := Lookup(tc.otherEncoding)
if e == nil {
t.Errorf("%s: not found", tc.otherEncoding)
continue
}
s, err := transformString(e.NewEncoder(), tc.utf8)
if err != nil {
t.Errorf("%s: encode %q: %s", tc.otherEncoding, tc.utf8, err)
continue
}
if s != tc.other {
t.Errorf("%s: got %q, want %q", tc.otherEncoding, s, tc.other)
}
}
}
// TestNames verifies that you can pass an encoding's name to Lookup and get
// the same encoding back (except for "replacement").
func TestNames(t *testing.T) {
for _, e := range encodings {
if e.name == "replacement" {
continue
}
_, got := Lookup(e.name)
if got != e.name {
t.Errorf("got %q, want %q", got, e.name)
continue
}
}
}
var sniffTestCases = []struct {
filename, declared, want string
}{
{"HTTP-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"UTF-16LE-BOM.html", "", "utf-16le"},
{"UTF-16BE-BOM.html", "", "utf-16be"},
{"meta-content-attribute.html", "text/html", "iso-8859-15"},
{"meta-charset-attribute.html", "text/html", "iso-8859-15"},
{"No-encoding-declaration.html", "text/html", "utf-8"},
{"HTTP-vs-UTF-8-BOM.html", "text/html; charset=iso-8859-15", "utf-8"},
{"HTTP-vs-meta-content.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"HTTP-vs-meta-charset.html", "text/html; charset=iso-8859-15", "iso-8859-15"},
{"UTF-8-BOM-vs-meta-content.html", "text/html", "utf-8"},
{"UTF-8-BOM-vs-meta-charset.html", "text/html", "utf-8"},
}
func TestSniff(t *testing.T) {
switch runtime.GOOS {
case "nacl": // platforms that don't permit direct file system access
t.Skipf("not supported on %q", runtime.GOOS)
}
for _, tc := range sniffTestCases {
content, err := ioutil.ReadFile("testdata/" + tc.filename)
if err != nil {
t.Errorf("%s: error reading file: %v", tc.filename, err)
continue
}
_, name, _ := DetermineEncoding(content, tc.declared)
if name != tc.want {
t.Errorf("%s: got %q, want %q", tc.filename, name, tc.want)
continue
}
}
}
func TestReader(t *testing.T) {
switch runtime.GOOS {
case "nacl": // platforms that don't permit direct file system access
t.Skipf("not supported on %q", runtime.GOOS)
}
for _, tc := range sniffTestCases {
content, err := ioutil.ReadFile("testdata/" + tc.filename)
if err != nil {
t.Errorf("%s: error reading file: %v", tc.filename, err)
continue
}
r, err := NewReader(bytes.NewReader(content), tc.declared)
if err != nil {
t.Errorf("%s: error creating reader: %v", tc.filename, err)
continue
}
got, err := ioutil.ReadAll(r)
if err != nil {
t.Errorf("%s: error reading from charset.NewReader: %v", tc.filename, err)
continue
}
e, _ := Lookup(tc.want)
want, err := ioutil.ReadAll(transform.NewReader(bytes.NewReader(content), e.NewDecoder()))
if err != nil {
t.Errorf("%s: error decoding with hard-coded charset name: %v", tc.filename, err)
continue
}
if !bytes.Equal(got, want) {
t.Errorf("%s: got %q, want %q", tc.filename, got, want)
continue
}
}
}
var metaTestCases = []struct {
meta, want string
}{
{"", ""},
{"text/html", ""},
{"text/html; charset utf-8", ""},
{"text/html; charset=latin-2", "latin-2"},
{"text/html; charset; charset = utf-8", "utf-8"},
{`charset="big5"`, "big5"},
{"charset='shift_jis'", "shift_jis"},
}
func TestFromMeta(t *testing.T) {
for _, tc := range metaTestCases {
got := fromMetaElement(tc.meta)
if got != tc.want {
t.Errorf("%q: got %q, want %q", tc.meta, got, tc.want)
}
}
}
func TestXML(t *testing.T) {
const s = "<?xml version=\"1.0\" encoding=\"windows-1252\"?><a><Word>r\xe9sum\xe9</Word></a>"
d := xml.NewDecoder(strings.NewReader(s))
d.CharsetReader = NewReaderLabel
var a struct {
Word string
}
err := d.Decode(&a)
if err != nil {
t.Fatalf("Decode: %v", err)
}
want := "résumé"
if a.Word != want {
t.Errorf("got %q, want %q", a.Word, want)
}
}

View File

@ -0,0 +1,111 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// +build ignore
package main
// Download https://encoding.spec.whatwg.org/encodings.json and use it to
// generate table.go.
import (
"encoding/json"
"fmt"
"log"
"net/http"
"strings"
)
type enc struct {
Name string
Labels []string
}
type group struct {
Encodings []enc
Heading string
}
const specURL = "https://encoding.spec.whatwg.org/encodings.json"
func main() {
resp, err := http.Get(specURL)
if err != nil {
log.Fatalf("error fetching %s: %s", specURL, err)
}
if resp.StatusCode != 200 {
log.Fatalf("error fetching %s: HTTP status %s", specURL, resp.Status)
}
defer resp.Body.Close()
var groups []group
d := json.NewDecoder(resp.Body)
err = d.Decode(&groups)
if err != nil {
log.Fatalf("error reading encodings.json: %s", err)
}
fmt.Println("// generated by go run gen.go; DO NOT EDIT")
fmt.Println()
fmt.Println("package charset")
fmt.Println()
fmt.Println("import (")
fmt.Println(`"golang.org/x/text/encoding"`)
for _, pkg := range []string{"charmap", "japanese", "korean", "simplifiedchinese", "traditionalchinese", "unicode"} {
fmt.Printf("\"golang.org/x/text/encoding/%s\"\n", pkg)
}
fmt.Println(")")
fmt.Println()
fmt.Println("var encodings = map[string]struct{e encoding.Encoding; name string} {")
for _, g := range groups {
for _, e := range g.Encodings {
goName, ok := miscNames[e.Name]
if !ok {
for k, v := range prefixes {
if strings.HasPrefix(e.Name, k) {
goName = v + e.Name[len(k):]
break
}
}
if goName == "" {
log.Fatalf("unrecognized encoding name: %s", e.Name)
}
}
for _, label := range e.Labels {
fmt.Printf("%q: {%s, %q},\n", label, goName, e.Name)
}
}
}
fmt.Println("}")
}
var prefixes = map[string]string{
"iso-8859-": "charmap.ISO8859_",
"windows-": "charmap.Windows",
}
var miscNames = map[string]string{
"utf-8": "encoding.Nop",
"ibm866": "charmap.CodePage866",
"iso-8859-8-i": "charmap.ISO8859_8",
"koi8-r": "charmap.KOI8R",
"koi8-u": "charmap.KOI8U",
"macintosh": "charmap.Macintosh",
"x-mac-cyrillic": "charmap.MacintoshCyrillic",
"gbk": "simplifiedchinese.GBK",
"gb18030": "simplifiedchinese.GB18030",
"hz-gb-2312": "simplifiedchinese.HZGB2312",
"big5": "traditionalchinese.Big5",
"euc-jp": "japanese.EUCJP",
"iso-2022-jp": "japanese.ISO2022JP",
"shift_jis": "japanese.ShiftJIS",
"euc-kr": "korean.EUCKR",
"replacement": "encoding.Replacement",
"utf-16be": "unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM)",
"utf-16le": "unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM)",
"x-user-defined": "charmap.XUserDefined",
}

View File

@ -0,0 +1,235 @@
// generated by go run gen.go; DO NOT EDIT
package charset
import (
"golang.org/x/text/encoding"
"golang.org/x/text/encoding/charmap"
"golang.org/x/text/encoding/japanese"
"golang.org/x/text/encoding/korean"
"golang.org/x/text/encoding/simplifiedchinese"
"golang.org/x/text/encoding/traditionalchinese"
"golang.org/x/text/encoding/unicode"
)
var encodings = map[string]struct {
e encoding.Encoding
name string
}{
"unicode-1-1-utf-8": {encoding.Nop, "utf-8"},
"utf-8": {encoding.Nop, "utf-8"},
"utf8": {encoding.Nop, "utf-8"},
"866": {charmap.CodePage866, "ibm866"},
"cp866": {charmap.CodePage866, "ibm866"},
"csibm866": {charmap.CodePage866, "ibm866"},
"ibm866": {charmap.CodePage866, "ibm866"},
"csisolatin2": {charmap.ISO8859_2, "iso-8859-2"},
"iso-8859-2": {charmap.ISO8859_2, "iso-8859-2"},
"iso-ir-101": {charmap.ISO8859_2, "iso-8859-2"},
"iso8859-2": {charmap.ISO8859_2, "iso-8859-2"},
"iso88592": {charmap.ISO8859_2, "iso-8859-2"},
"iso_8859-2": {charmap.ISO8859_2, "iso-8859-2"},
"iso_8859-2:1987": {charmap.ISO8859_2, "iso-8859-2"},
"l2": {charmap.ISO8859_2, "iso-8859-2"},
"latin2": {charmap.ISO8859_2, "iso-8859-2"},
"csisolatin3": {charmap.ISO8859_3, "iso-8859-3"},
"iso-8859-3": {charmap.ISO8859_3, "iso-8859-3"},
"iso-ir-109": {charmap.ISO8859_3, "iso-8859-3"},
"iso8859-3": {charmap.ISO8859_3, "iso-8859-3"},
"iso88593": {charmap.ISO8859_3, "iso-8859-3"},
"iso_8859-3": {charmap.ISO8859_3, "iso-8859-3"},
"iso_8859-3:1988": {charmap.ISO8859_3, "iso-8859-3"},
"l3": {charmap.ISO8859_3, "iso-8859-3"},
"latin3": {charmap.ISO8859_3, "iso-8859-3"},
"csisolatin4": {charmap.ISO8859_4, "iso-8859-4"},
"iso-8859-4": {charmap.ISO8859_4, "iso-8859-4"},
"iso-ir-110": {charmap.ISO8859_4, "iso-8859-4"},
"iso8859-4": {charmap.ISO8859_4, "iso-8859-4"},
"iso88594": {charmap.ISO8859_4, "iso-8859-4"},
"iso_8859-4": {charmap.ISO8859_4, "iso-8859-4"},
"iso_8859-4:1988": {charmap.ISO8859_4, "iso-8859-4"},
"l4": {charmap.ISO8859_4, "iso-8859-4"},
"latin4": {charmap.ISO8859_4, "iso-8859-4"},
"csisolatincyrillic": {charmap.ISO8859_5, "iso-8859-5"},
"cyrillic": {charmap.ISO8859_5, "iso-8859-5"},
"iso-8859-5": {charmap.ISO8859_5, "iso-8859-5"},
"iso-ir-144": {charmap.ISO8859_5, "iso-8859-5"},
"iso8859-5": {charmap.ISO8859_5, "iso-8859-5"},
"iso88595": {charmap.ISO8859_5, "iso-8859-5"},
"iso_8859-5": {charmap.ISO8859_5, "iso-8859-5"},
"iso_8859-5:1988": {charmap.ISO8859_5, "iso-8859-5"},
"arabic": {charmap.ISO8859_6, "iso-8859-6"},
"asmo-708": {charmap.ISO8859_6, "iso-8859-6"},
"csiso88596e": {charmap.ISO8859_6, "iso-8859-6"},
"csiso88596i": {charmap.ISO8859_6, "iso-8859-6"},
"csisolatinarabic": {charmap.ISO8859_6, "iso-8859-6"},
"ecma-114": {charmap.ISO8859_6, "iso-8859-6"},
"iso-8859-6": {charmap.ISO8859_6, "iso-8859-6"},
"iso-8859-6-e": {charmap.ISO8859_6, "iso-8859-6"},
"iso-8859-6-i": {charmap.ISO8859_6, "iso-8859-6"},
"iso-ir-127": {charmap.ISO8859_6, "iso-8859-6"},
"iso8859-6": {charmap.ISO8859_6, "iso-8859-6"},
"iso88596": {charmap.ISO8859_6, "iso-8859-6"},
"iso_8859-6": {charmap.ISO8859_6, "iso-8859-6"},
"iso_8859-6:1987": {charmap.ISO8859_6, "iso-8859-6"},
"csisolatingreek": {charmap.ISO8859_7, "iso-8859-7"},
"ecma-118": {charmap.ISO8859_7, "iso-8859-7"},
"elot_928": {charmap.ISO8859_7, "iso-8859-7"},
"greek": {charmap.ISO8859_7, "iso-8859-7"},
"greek8": {charmap.ISO8859_7, "iso-8859-7"},
"iso-8859-7": {charmap.ISO8859_7, "iso-8859-7"},
"iso-ir-126": {charmap.ISO8859_7, "iso-8859-7"},
"iso8859-7": {charmap.ISO8859_7, "iso-8859-7"},
"iso88597": {charmap.ISO8859_7, "iso-8859-7"},
"iso_8859-7": {charmap.ISO8859_7, "iso-8859-7"},
"iso_8859-7:1987": {charmap.ISO8859_7, "iso-8859-7"},
"sun_eu_greek": {charmap.ISO8859_7, "iso-8859-7"},
"csiso88598e": {charmap.ISO8859_8, "iso-8859-8"},
"csisolatinhebrew": {charmap.ISO8859_8, "iso-8859-8"},
"hebrew": {charmap.ISO8859_8, "iso-8859-8"},
"iso-8859-8": {charmap.ISO8859_8, "iso-8859-8"},
"iso-8859-8-e": {charmap.ISO8859_8, "iso-8859-8"},
"iso-ir-138": {charmap.ISO8859_8, "iso-8859-8"},
"iso8859-8": {charmap.ISO8859_8, "iso-8859-8"},
"iso88598": {charmap.ISO8859_8, "iso-8859-8"},
"iso_8859-8": {charmap.ISO8859_8, "iso-8859-8"},
"iso_8859-8:1988": {charmap.ISO8859_8, "iso-8859-8"},
"visual": {charmap.ISO8859_8, "iso-8859-8"},
"csiso88598i": {charmap.ISO8859_8, "iso-8859-8-i"},
"iso-8859-8-i": {charmap.ISO8859_8, "iso-8859-8-i"},
"logical": {charmap.ISO8859_8, "iso-8859-8-i"},
"csisolatin6": {charmap.ISO8859_10, "iso-8859-10"},
"iso-8859-10": {charmap.ISO8859_10, "iso-8859-10"},
"iso-ir-157": {charmap.ISO8859_10, "iso-8859-10"},
"iso8859-10": {charmap.ISO8859_10, "iso-8859-10"},
"iso885910": {charmap.ISO8859_10, "iso-8859-10"},
"l6": {charmap.ISO8859_10, "iso-8859-10"},
"latin6": {charmap.ISO8859_10, "iso-8859-10"},
"iso-8859-13": {charmap.ISO8859_13, "iso-8859-13"},
"iso8859-13": {charmap.ISO8859_13, "iso-8859-13"},
"iso885913": {charmap.ISO8859_13, "iso-8859-13"},
"iso-8859-14": {charmap.ISO8859_14, "iso-8859-14"},
"iso8859-14": {charmap.ISO8859_14, "iso-8859-14"},
"iso885914": {charmap.ISO8859_14, "iso-8859-14"},
"csisolatin9": {charmap.ISO8859_15, "iso-8859-15"},
"iso-8859-15": {charmap.ISO8859_15, "iso-8859-15"},
"iso8859-15": {charmap.ISO8859_15, "iso-8859-15"},
"iso885915": {charmap.ISO8859_15, "iso-8859-15"},
"iso_8859-15": {charmap.ISO8859_15, "iso-8859-15"},
"l9": {charmap.ISO8859_15, "iso-8859-15"},
"iso-8859-16": {charmap.ISO8859_16, "iso-8859-16"},
"cskoi8r": {charmap.KOI8R, "koi8-r"},
"koi": {charmap.KOI8R, "koi8-r"},
"koi8": {charmap.KOI8R, "koi8-r"},
"koi8-r": {charmap.KOI8R, "koi8-r"},
"koi8_r": {charmap.KOI8R, "koi8-r"},
"koi8-u": {charmap.KOI8U, "koi8-u"},
"csmacintosh": {charmap.Macintosh, "macintosh"},
"mac": {charmap.Macintosh, "macintosh"},
"macintosh": {charmap.Macintosh, "macintosh"},
"x-mac-roman": {charmap.Macintosh, "macintosh"},
"dos-874": {charmap.Windows874, "windows-874"},
"iso-8859-11": {charmap.Windows874, "windows-874"},
"iso8859-11": {charmap.Windows874, "windows-874"},
"iso885911": {charmap.Windows874, "windows-874"},
"tis-620": {charmap.Windows874, "windows-874"},
"windows-874": {charmap.Windows874, "windows-874"},
"cp1250": {charmap.Windows1250, "windows-1250"},
"windows-1250": {charmap.Windows1250, "windows-1250"},
"x-cp1250": {charmap.Windows1250, "windows-1250"},
"cp1251": {charmap.Windows1251, "windows-1251"},
"windows-1251": {charmap.Windows1251, "windows-1251"},
"x-cp1251": {charmap.Windows1251, "windows-1251"},
"ansi_x3.4-1968": {charmap.Windows1252, "windows-1252"},
"ascii": {charmap.Windows1252, "windows-1252"},
"cp1252": {charmap.Windows1252, "windows-1252"},
"cp819": {charmap.Windows1252, "windows-1252"},
"csisolatin1": {charmap.Windows1252, "windows-1252"},
"ibm819": {charmap.Windows1252, "windows-1252"},
"iso-8859-1": {charmap.Windows1252, "windows-1252"},
"iso-ir-100": {charmap.Windows1252, "windows-1252"},
"iso8859-1": {charmap.Windows1252, "windows-1252"},
"iso88591": {charmap.Windows1252, "windows-1252"},
"iso_8859-1": {charmap.Windows1252, "windows-1252"},
"iso_8859-1:1987": {charmap.Windows1252, "windows-1252"},
"l1": {charmap.Windows1252, "windows-1252"},
"latin1": {charmap.Windows1252, "windows-1252"},
"us-ascii": {charmap.Windows1252, "windows-1252"},
"windows-1252": {charmap.Windows1252, "windows-1252"},
"x-cp1252": {charmap.Windows1252, "windows-1252"},
"cp1253": {charmap.Windows1253, "windows-1253"},
"windows-1253": {charmap.Windows1253, "windows-1253"},
"x-cp1253": {charmap.Windows1253, "windows-1253"},
"cp1254": {charmap.Windows1254, "windows-1254"},
"csisolatin5": {charmap.Windows1254, "windows-1254"},
"iso-8859-9": {charmap.Windows1254, "windows-1254"},
"iso-ir-148": {charmap.Windows1254, "windows-1254"},
"iso8859-9": {charmap.Windows1254, "windows-1254"},
"iso88599": {charmap.Windows1254, "windows-1254"},
"iso_8859-9": {charmap.Windows1254, "windows-1254"},
"iso_8859-9:1989": {charmap.Windows1254, "windows-1254"},
"l5": {charmap.Windows1254, "windows-1254"},
"latin5": {charmap.Windows1254, "windows-1254"},
"windows-1254": {charmap.Windows1254, "windows-1254"},
"x-cp1254": {charmap.Windows1254, "windows-1254"},
"cp1255": {charmap.Windows1255, "windows-1255"},
"windows-1255": {charmap.Windows1255, "windows-1255"},
"x-cp1255": {charmap.Windows1255, "windows-1255"},
"cp1256": {charmap.Windows1256, "windows-1256"},
"windows-1256": {charmap.Windows1256, "windows-1256"},
"x-cp1256": {charmap.Windows1256, "windows-1256"},
"cp1257": {charmap.Windows1257, "windows-1257"},
"windows-1257": {charmap.Windows1257, "windows-1257"},
"x-cp1257": {charmap.Windows1257, "windows-1257"},
"cp1258": {charmap.Windows1258, "windows-1258"},
"windows-1258": {charmap.Windows1258, "windows-1258"},
"x-cp1258": {charmap.Windows1258, "windows-1258"},
"x-mac-cyrillic": {charmap.MacintoshCyrillic, "x-mac-cyrillic"},
"x-mac-ukrainian": {charmap.MacintoshCyrillic, "x-mac-cyrillic"},
"chinese": {simplifiedchinese.GBK, "gbk"},
"csgb2312": {simplifiedchinese.GBK, "gbk"},
"csiso58gb231280": {simplifiedchinese.GBK, "gbk"},
"gb2312": {simplifiedchinese.GBK, "gbk"},
"gb_2312": {simplifiedchinese.GBK, "gbk"},
"gb_2312-80": {simplifiedchinese.GBK, "gbk"},
"gbk": {simplifiedchinese.GBK, "gbk"},
"iso-ir-58": {simplifiedchinese.GBK, "gbk"},
"x-gbk": {simplifiedchinese.GBK, "gbk"},
"gb18030": {simplifiedchinese.GB18030, "gb18030"},
"hz-gb-2312": {simplifiedchinese.HZGB2312, "hz-gb-2312"},
"big5": {traditionalchinese.Big5, "big5"},
"big5-hkscs": {traditionalchinese.Big5, "big5"},
"cn-big5": {traditionalchinese.Big5, "big5"},
"csbig5": {traditionalchinese.Big5, "big5"},
"x-x-big5": {traditionalchinese.Big5, "big5"},
"cseucpkdfmtjapanese": {japanese.EUCJP, "euc-jp"},
"euc-jp": {japanese.EUCJP, "euc-jp"},
"x-euc-jp": {japanese.EUCJP, "euc-jp"},
"csiso2022jp": {japanese.ISO2022JP, "iso-2022-jp"},
"iso-2022-jp": {japanese.ISO2022JP, "iso-2022-jp"},
"csshiftjis": {japanese.ShiftJIS, "shift_jis"},
"ms_kanji": {japanese.ShiftJIS, "shift_jis"},
"shift-jis": {japanese.ShiftJIS, "shift_jis"},
"shift_jis": {japanese.ShiftJIS, "shift_jis"},
"sjis": {japanese.ShiftJIS, "shift_jis"},
"windows-31j": {japanese.ShiftJIS, "shift_jis"},
"x-sjis": {japanese.ShiftJIS, "shift_jis"},
"cseuckr": {korean.EUCKR, "euc-kr"},
"csksc56011987": {korean.EUCKR, "euc-kr"},
"euc-kr": {korean.EUCKR, "euc-kr"},
"iso-ir-149": {korean.EUCKR, "euc-kr"},
"korean": {korean.EUCKR, "euc-kr"},
"ks_c_5601-1987": {korean.EUCKR, "euc-kr"},
"ks_c_5601-1989": {korean.EUCKR, "euc-kr"},
"ksc5601": {korean.EUCKR, "euc-kr"},
"ksc_5601": {korean.EUCKR, "euc-kr"},
"windows-949": {korean.EUCKR, "euc-kr"},
"csiso2022kr": {encoding.Replacement, "replacement"},
"iso-2022-kr": {encoding.Replacement, "replacement"},
"iso-2022-cn": {encoding.Replacement, "replacement"},
"iso-2022-cn-ext": {encoding.Replacement, "replacement"},
"utf-16be": {unicode.UTF16(unicode.BigEndian, unicode.IgnoreBOM), "utf-16be"},
"utf-16": {unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM), "utf-16le"},
"utf-16le": {unicode.UTF16(unicode.LittleEndian, unicode.IgnoreBOM), "utf-16le"},
"x-user-defined": {charmap.XUserDefined, "x-user-defined"},
}

View File

@ -0,0 +1,48 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<title>HTTP charset</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="The character encoding of a page can be set using the HTTP header charset declaration.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
</head>
<body>
<p class='title'>HTTP charset</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">The character encoding of a page can be set using the HTTP header charset declaration.</p>
<div class="notes"><p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p><p>The only character encoding declaration for this HTML file is in the HTTP header, which sets the encoding to ISO 8859-15.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-003">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-001<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-001" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,48 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<title>HTTP vs UTF-8 BOM</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="A character encoding set in the HTTP header has lower precedence than the UTF-8 signature.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
</head>
<body>
<p class='title'>HTTP vs UTF-8 BOM</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">A character encoding set in the HTTP header has lower precedence than the UTF-8 signature.</p>
<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p><p>If the test is unsuccessful, the characters &#x00EF;&#x00BB;&#x00BF; should appear at the top of the page. These represent the bytes that make up the UTF-8 signature when encountered in the ISO 8859-15 encoding.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-022">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-034<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-034" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,49 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta charset="iso-8859-1" > <title>HTTP vs meta charset</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="The HTTP header has a higher precedence than an encoding declaration in a meta charset attribute.">
<style type='text/css'>
.test div { width: 50px; }.test div { width: 90px; }
</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
</head>
<body>
<p class='title'>HTTP vs meta charset</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">The HTTP header has a higher precedence than an encoding declaration in a meta charset attribute.</p>
<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page contains an encoding declaration in a meta charset attribute that attempts to set the character encoding to ISO 8859-1.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-037">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-018<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-018" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,49 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta http-equiv="content-type" content="text/html;charset=iso-8859-1" > <title>HTTP vs meta content</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="The HTTP header has a higher precedence than an encoding declaration in a meta content attribute.">
<style type='text/css'>
.test div { width: 50px; }.test div { width: 90px; }
</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
</head>
<body>
<p class='title'>HTTP vs meta content</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">The HTTP header has a higher precedence than an encoding declaration in a meta content attribute.</p>
<div class="notes"><p><p>The HTTP header attempts to set the character encoding to ISO 8859-15. The page contains an encoding declaration in a meta content attribute that attempts to set the character encoding to ISO 8859-1.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-018">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-016<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-016" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,47 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<title>No encoding declaration</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="A page with no encoding information in HTTP, BOM, XML declaration or meta element will be treated as UTF-8.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
</head>
<body>
<p class='title'>No encoding declaration</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">A page with no encoding information in HTTP, BOM, XML declaration or meta element will be treated as UTF-8.</p>
<div class="notes"><p><p>The test on this page contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-034">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-015<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-015" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,9 @@
These test cases come from
http://www.w3.org/International/tests/repository/html5/the-input-byte-stream/results-basics
Distributed under both the W3C Test Suite License
(http://www.w3.org/Consortium/Legal/2008/04-testsuite-license)
and the W3C 3-clause BSD License
(http://www.w3.org/Consortium/Legal/2008/03-bsd-license).
To contribute to a W3C Test Suite, see the policies and contribution
forms (http://www.w3.org/2004/10/27-testcases).

Binary file not shown.

Binary file not shown.

View File

@ -0,0 +1,49 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta charset="iso-8859-15"> <title>UTF-8 BOM vs meta charset</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta charset attribute declares a different encoding.">
<style type='text/css'>
.test div { width: 50px; }.test div { width: 90px; }
</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
</head>
<body>
<p class='title'>UTF-8 BOM vs meta charset</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta charset attribute declares a different encoding.</p>
<div class="notes"><p><p>The page contains an encoding declaration in a meta charset attribute that attempts to set the character encoding to ISO 8859-15, but the file starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-024">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-038<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-038" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,48 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta http-equiv="content-type" content="text/html; charset=iso-8859-15"> <title>UTF-8 BOM vs meta content</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta content attribute declares a different encoding.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-utf8.css">
</head>
<body>
<p class='title'>UTF-8 BOM vs meta content</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">A page with a UTF-8 BOM will be recognized as UTF-8 even if the meta content attribute declares a different encoding.</p>
<div class="notes"><p><p>The page contains an encoding declaration in a meta content attribute that attempts to set the character encoding to ISO 8859-15, but the file starts with a UTF-8 signature.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00FD;&#x00E4;&#x00E8;</code>. This matches the sequence of bytes above when they are interpreted as UTF-8. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-038">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-037<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#precedence" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-037" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,48 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta charset="iso-8859-15"> <title>meta charset attribute</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="The character encoding of the page can be set by a meta element with charset attribute.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
</head>
<body>
<p class='title'>meta charset attribute</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">The character encoding of the page can be set by a meta element with charset attribute.</p>
<div class="notes"><p><p>The only character encoding declaration for this HTML file is in the charset attribute of the meta element, which declares the encoding to be ISO 8859-15.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-015">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-009<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-009" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

View File

@ -0,0 +1,48 @@
<!DOCTYPE html>
<html lang="en" >
<head>
<meta http-equiv="content-type" content="text/html; charset=iso-8859-15"> <title>meta content attribute</title>
<link rel='author' title='Richard Ishida' href='mailto:ishida@w3.org'>
<link rel='help' href='http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream'>
<link rel="stylesheet" type="text/css" href="./generatedtests.css">
<script src="http://w3c-test.org/resources/testharness.js"></script>
<script src="http://w3c-test.org/resources/testharnessreport.js"></script>
<meta name='flags' content='http'>
<meta name="assert" content="The character encoding of the page can be set by a meta element with http-equiv and content attributes.">
<style type='text/css'>
.test div { width: 50px; }</style>
<link rel="stylesheet" type="text/css" href="the-input-byte-stream/support/encodingtests-15.css">
</head>
<body>
<p class='title'>meta content attribute</p>
<div id='log'></div>
<div class='test'><div id='box' class='ýäè'>&#xA0;</div></div>
<div class='description'>
<p class="assertion" title="Assertion">The character encoding of the page can be set by a meta element with http-equiv and content attributes.</p>
<div class="notes"><p><p>The only character encoding declaration for this HTML file is in the content attribute of the meta element, which declares the encoding to be ISO 8859-15.</p><p>The test contains a div with a class name that contains the following sequence of bytes: 0xC3 0xBD 0xC3 0xA4 0xC3 0xA8. These represent different sequences of characters in ISO 8859-15, ISO 8859-1 and UTF-8. The external, UTF-8-encoded stylesheet contains a selector <code>.test div.&#x00C3;&#x0153;&#x00C3;&#x20AC;&#x00C3;&#x0161;</code>. This matches the sequence of bytes above when they are interpreted as ISO 8859-15. If the class name matches the selector then the test will pass.</p></p>
</div>
</div>
<div class="nexttest"><div><a href="generate?test=the-input-byte-stream-009">Next test</a></div><div class="doctype">HTML5</div>
<p class="jump">the-input-byte-stream-007<br /><a href="/International/tests/html5/the-input-byte-stream/results-basics#basics" target="_blank">Result summary &amp; related tests</a><br /><a href="http://w3c-test.org/framework/details/i18n-html5/the-input-byte-stream-007" target="_blank">Detailed results for this test</a><br/> <a href="http://www.w3.org/TR/html5/syntax.html#the-input-byte-stream" target="_blank">Link to spec</a></p>
<div class='prereq'>Assumptions: <ul><li>The default encoding for the browser you are testing is not set to ISO 8859-15.</li>
<li>The test is read from a server that supports HTTP.</li></ul></div>
</div>
<script>
test(function() {
assert_equals(document.getElementById('box').offsetWidth, 100);
}, " ");
</script>
</body>
</html>

102
Godeps/_workspace/src/golang.org/x/net/html/const.go generated vendored Normal file
View File

@ -0,0 +1,102 @@
// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
// Section 12.2.3.2 of the HTML5 specification says "The following elements
// have varying levels of special parsing rules".
// https://html.spec.whatwg.org/multipage/syntax.html#the-stack-of-open-elements
var isSpecialElementMap = map[string]bool{
"address": true,
"applet": true,
"area": true,
"article": true,
"aside": true,
"base": true,
"basefont": true,
"bgsound": true,
"blockquote": true,
"body": true,
"br": true,
"button": true,
"caption": true,
"center": true,
"col": true,
"colgroup": true,
"dd": true,
"details": true,
"dir": true,
"div": true,
"dl": true,
"dt": true,
"embed": true,
"fieldset": true,
"figcaption": true,
"figure": true,
"footer": true,
"form": true,
"frame": true,
"frameset": true,
"h1": true,
"h2": true,
"h3": true,
"h4": true,
"h5": true,
"h6": true,
"head": true,
"header": true,
"hgroup": true,
"hr": true,
"html": true,
"iframe": true,
"img": true,
"input": true,
"isindex": true,
"li": true,
"link": true,
"listing": true,
"marquee": true,
"menu": true,
"meta": true,
"nav": true,
"noembed": true,
"noframes": true,
"noscript": true,
"object": true,
"ol": true,
"p": true,
"param": true,
"plaintext": true,
"pre": true,
"script": true,
"section": true,
"select": true,
"source": true,
"style": true,
"summary": true,
"table": true,
"tbody": true,
"td": true,
"template": true,
"textarea": true,
"tfoot": true,
"th": true,
"thead": true,
"title": true,
"tr": true,
"track": true,
"ul": true,
"wbr": true,
"xmp": true,
}
func isSpecialElement(element *Node) bool {
switch element.Namespace {
case "", "html":
return isSpecialElementMap[element.Data]
case "svg":
return element.Data == "foreignObject"
}
return false
}

106
Godeps/_workspace/src/golang.org/x/net/html/doc.go generated vendored Normal file
View File

@ -0,0 +1,106 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
/*
Package html implements an HTML5-compliant tokenizer and parser.
Tokenization is done by creating a Tokenizer for an io.Reader r. It is the
caller's responsibility to ensure that r provides UTF-8 encoded HTML.
z := html.NewTokenizer(r)
Given a Tokenizer z, the HTML is tokenized by repeatedly calling z.Next(),
which parses the next token and returns its type, or an error:
for {
tt := z.Next()
if tt == html.ErrorToken {
// ...
return ...
}
// Process the current token.
}
There are two APIs for retrieving the current token. The high-level API is to
call Token; the low-level API is to call Text or TagName / TagAttr. Both APIs
allow optionally calling Raw after Next but before Token, Text, TagName, or
TagAttr. In EBNF notation, the valid call sequence per token is:
Next {Raw} [ Token | Text | TagName {TagAttr} ]
Token returns an independent data structure that completely describes a token.
Entities (such as "&lt;") are unescaped, tag names and attribute keys are
lower-cased, and attributes are collected into a []Attribute. For example:
for {
if z.Next() == html.ErrorToken {
// Returning io.EOF indicates success.
return z.Err()
}
emitToken(z.Token())
}
The low-level API performs fewer allocations and copies, but the contents of
the []byte values returned by Text, TagName and TagAttr may change on the next
call to Next. For example, to extract an HTML page's anchor text:
depth := 0
for {
tt := z.Next()
switch tt {
case ErrorToken:
return z.Err()
case TextToken:
if depth > 0 {
// emitBytes should copy the []byte it receives,
// if it doesn't process it immediately.
emitBytes(z.Text())
}
case StartTagToken, EndTagToken:
tn, _ := z.TagName()
if len(tn) == 1 && tn[0] == 'a' {
if tt == StartTagToken {
depth++
} else {
depth--
}
}
}
}
Parsing is done by calling Parse with an io.Reader, which returns the root of
the parse tree (the document element) as a *Node. It is the caller's
responsibility to ensure that the Reader provides UTF-8 encoded HTML. For
example, to process each anchor node in depth-first order:
doc, err := html.Parse(r)
if err != nil {
// ...
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
// Do something with n...
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
The relevant specifications include:
https://html.spec.whatwg.org/multipage/syntax.html and
https://html.spec.whatwg.org/multipage/syntax.html#tokenization
*/
package html
// The tokenization algorithm implemented by this package is not a line-by-line
// transliteration of the relatively verbose state-machine in the WHATWG
// specification. A more direct approach is used instead, where the program
// counter implies the state, such as whether it is tokenizing a tag or a text
// node. Specification compliance is verified by checking expected and actual
// outputs over a test suite rather than aiming for algorithmic fidelity.
// TODO(nigeltao): Does a DOM API belong in this package or a separate one?
// TODO(nigeltao): How does parsing interact with a JavaScript engine?

156
Godeps/_workspace/src/golang.org/x/net/html/doctype.go generated vendored Normal file
View File

@ -0,0 +1,156 @@
// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"strings"
)
// parseDoctype parses the data from a DoctypeToken into a name,
// public identifier, and system identifier. It returns a Node whose Type
// is DoctypeNode, whose Data is the name, and which has attributes
// named "system" and "public" for the two identifiers if they were present.
// quirks is whether the document should be parsed in "quirks mode".
func parseDoctype(s string) (n *Node, quirks bool) {
n = &Node{Type: DoctypeNode}
// Find the name.
space := strings.IndexAny(s, whitespace)
if space == -1 {
space = len(s)
}
n.Data = s[:space]
// The comparison to "html" is case-sensitive.
if n.Data != "html" {
quirks = true
}
n.Data = strings.ToLower(n.Data)
s = strings.TrimLeft(s[space:], whitespace)
if len(s) < 6 {
// It can't start with "PUBLIC" or "SYSTEM".
// Ignore the rest of the string.
return n, quirks || s != ""
}
key := strings.ToLower(s[:6])
s = s[6:]
for key == "public" || key == "system" {
s = strings.TrimLeft(s, whitespace)
if s == "" {
break
}
quote := s[0]
if quote != '"' && quote != '\'' {
break
}
s = s[1:]
q := strings.IndexRune(s, rune(quote))
var id string
if q == -1 {
id = s
s = ""
} else {
id = s[:q]
s = s[q+1:]
}
n.Attr = append(n.Attr, Attribute{Key: key, Val: id})
if key == "public" {
key = "system"
} else {
key = ""
}
}
if key != "" || s != "" {
quirks = true
} else if len(n.Attr) > 0 {
if n.Attr[0].Key == "public" {
public := strings.ToLower(n.Attr[0].Val)
switch public {
case "-//w3o//dtd w3 html strict 3.0//en//", "-/w3d/dtd html 4.0 transitional/en", "html":
quirks = true
default:
for _, q := range quirkyIDs {
if strings.HasPrefix(public, q) {
quirks = true
break
}
}
}
// The following two public IDs only cause quirks mode if there is no system ID.
if len(n.Attr) == 1 && (strings.HasPrefix(public, "-//w3c//dtd html 4.01 frameset//") ||
strings.HasPrefix(public, "-//w3c//dtd html 4.01 transitional//")) {
quirks = true
}
}
if lastAttr := n.Attr[len(n.Attr)-1]; lastAttr.Key == "system" &&
strings.ToLower(lastAttr.Val) == "http://www.ibm.com/data/dtd/v11/ibmxhtml1-transitional.dtd" {
quirks = true
}
}
return n, quirks
}
// quirkyIDs is a list of public doctype identifiers that cause a document
// to be interpreted in quirks mode. The identifiers should be in lower case.
var quirkyIDs = []string{
"+//silmaril//dtd html pro v0r11 19970101//",
"-//advasoft ltd//dtd html 3.0 aswedit + extensions//",
"-//as//dtd html 3.0 aswedit + extensions//",
"-//ietf//dtd html 2.0 level 1//",
"-//ietf//dtd html 2.0 level 2//",
"-//ietf//dtd html 2.0 strict level 1//",
"-//ietf//dtd html 2.0 strict level 2//",
"-//ietf//dtd html 2.0 strict//",
"-//ietf//dtd html 2.0//",
"-//ietf//dtd html 2.1e//",
"-//ietf//dtd html 3.0//",
"-//ietf//dtd html 3.2 final//",
"-//ietf//dtd html 3.2//",
"-//ietf//dtd html 3//",
"-//ietf//dtd html level 0//",
"-//ietf//dtd html level 1//",
"-//ietf//dtd html level 2//",
"-//ietf//dtd html level 3//",
"-//ietf//dtd html strict level 0//",
"-//ietf//dtd html strict level 1//",
"-//ietf//dtd html strict level 2//",
"-//ietf//dtd html strict level 3//",
"-//ietf//dtd html strict//",
"-//ietf//dtd html//",
"-//metrius//dtd metrius presentational//",
"-//microsoft//dtd internet explorer 2.0 html strict//",
"-//microsoft//dtd internet explorer 2.0 html//",
"-//microsoft//dtd internet explorer 2.0 tables//",
"-//microsoft//dtd internet explorer 3.0 html strict//",
"-//microsoft//dtd internet explorer 3.0 html//",
"-//microsoft//dtd internet explorer 3.0 tables//",
"-//netscape comm. corp.//dtd html//",
"-//netscape comm. corp.//dtd strict html//",
"-//o'reilly and associates//dtd html 2.0//",
"-//o'reilly and associates//dtd html extended 1.0//",
"-//o'reilly and associates//dtd html extended relaxed 1.0//",
"-//softquad software//dtd hotmetal pro 6.0::19990601::extensions to html 4.0//",
"-//softquad//dtd hotmetal pro 4.0::19971010::extensions to html 4.0//",
"-//spyglass//dtd html 2.0 extended//",
"-//sq//dtd html 2.0 hotmetal + extensions//",
"-//sun microsystems corp.//dtd hotjava html//",
"-//sun microsystems corp.//dtd hotjava strict html//",
"-//w3c//dtd html 3 1995-03-24//",
"-//w3c//dtd html 3.2 draft//",
"-//w3c//dtd html 3.2 final//",
"-//w3c//dtd html 3.2//",
"-//w3c//dtd html 3.2s draft//",
"-//w3c//dtd html 4.0 frameset//",
"-//w3c//dtd html 4.0 transitional//",
"-//w3c//dtd html experimental 19960712//",
"-//w3c//dtd html experimental 970421//",
"-//w3c//dtd w3 html//",
"-//w3o//dtd w3 html 3.0//",
"-//webtechs//dtd mozilla html 2.0//",
"-//webtechs//dtd mozilla html//",
}

2253
Godeps/_workspace/src/golang.org/x/net/html/entity.go generated vendored Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,29 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"testing"
"unicode/utf8"
)
func TestEntityLength(t *testing.T) {
// We verify that the length of UTF-8 encoding of each value is <= 1 + len(key).
// The +1 comes from the leading "&". This property implies that the length of
// unescaped text is <= the length of escaped text.
for k, v := range entity {
if 1+len(k) < utf8.RuneLen(v) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v))
}
if len(k) > longestEntityWithoutSemicolon && k[len(k)-1] != ';' {
t.Errorf("entity name %s is %d characters, but longestEntityWithoutSemicolon=%d", k, len(k), longestEntityWithoutSemicolon)
}
}
for k, v := range entity2 {
if 1+len(k) < utf8.RuneLen(v[0])+utf8.RuneLen(v[1]) {
t.Error("escaped entity &" + k + " is shorter than its UTF-8 encoding " + string(v[0]) + string(v[1]))
}
}
}

258
Godeps/_workspace/src/golang.org/x/net/html/escape.go generated vendored Normal file
View File

@ -0,0 +1,258 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"bytes"
"strings"
"unicode/utf8"
)
// These replacements permit compatibility with old numeric entities that
// assumed Windows-1252 encoding.
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
var replacementTable = [...]rune{
'\u20AC', // First entry is what 0x80 should be replaced with.
'\u0081',
'\u201A',
'\u0192',
'\u201E',
'\u2026',
'\u2020',
'\u2021',
'\u02C6',
'\u2030',
'\u0160',
'\u2039',
'\u0152',
'\u008D',
'\u017D',
'\u008F',
'\u0090',
'\u2018',
'\u2019',
'\u201C',
'\u201D',
'\u2022',
'\u2013',
'\u2014',
'\u02DC',
'\u2122',
'\u0161',
'\u203A',
'\u0153',
'\u009D',
'\u017E',
'\u0178', // Last entry is 0x9F.
// 0x00->'\uFFFD' is handled programmatically.
// 0x0D->'\u000D' is a no-op.
}
// unescapeEntity reads an entity like "&lt;" from b[src:] and writes the
// corresponding "<" to b[dst:], returning the incremented dst and src cursors.
// Precondition: b[src] == '&' && dst <= src.
// attribute should be true if parsing an attribute value.
func unescapeEntity(b []byte, dst, src int, attribute bool) (dst1, src1 int) {
// https://html.spec.whatwg.org/multipage/syntax.html#consume-a-character-reference
// i starts at 1 because we already know that s[0] == '&'.
i, s := 1, b[src:]
if len(s) <= 1 {
b[dst] = b[src]
return dst + 1, src + 1
}
if s[i] == '#' {
if len(s) <= 3 { // We need to have at least "&#.".
b[dst] = b[src]
return dst + 1, src + 1
}
i++
c := s[i]
hex := false
if c == 'x' || c == 'X' {
hex = true
i++
}
x := '\x00'
for i < len(s) {
c = s[i]
i++
if hex {
if '0' <= c && c <= '9' {
x = 16*x + rune(c) - '0'
continue
} else if 'a' <= c && c <= 'f' {
x = 16*x + rune(c) - 'a' + 10
continue
} else if 'A' <= c && c <= 'F' {
x = 16*x + rune(c) - 'A' + 10
continue
}
} else if '0' <= c && c <= '9' {
x = 10*x + rune(c) - '0'
continue
}
if c != ';' {
i--
}
break
}
if i <= 3 { // No characters matched.
b[dst] = b[src]
return dst + 1, src + 1
}
if 0x80 <= x && x <= 0x9F {
// Replace characters from Windows-1252 with UTF-8 equivalents.
x = replacementTable[x-0x80]
} else if x == 0 || (0xD800 <= x && x <= 0xDFFF) || x > 0x10FFFF {
// Replace invalid characters with the replacement character.
x = '\uFFFD'
}
return dst + utf8.EncodeRune(b[dst:], x), src + i
}
// Consume the maximum number of characters possible, with the
// consumed characters matching one of the named references.
for i < len(s) {
c := s[i]
i++
// Lower-cased characters are more common in entities, so we check for them first.
if 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || '0' <= c && c <= '9' {
continue
}
if c != ';' {
i--
}
break
}
entityName := string(s[1:i])
if entityName == "" {
// No-op.
} else if attribute && entityName[len(entityName)-1] != ';' && len(s) > i && s[i] == '=' {
// No-op.
} else if x := entity[entityName]; x != 0 {
return dst + utf8.EncodeRune(b[dst:], x), src + i
} else if x := entity2[entityName]; x[0] != 0 {
dst1 := dst + utf8.EncodeRune(b[dst:], x[0])
return dst1 + utf8.EncodeRune(b[dst1:], x[1]), src + i
} else if !attribute {
maxLen := len(entityName) - 1
if maxLen > longestEntityWithoutSemicolon {
maxLen = longestEntityWithoutSemicolon
}
for j := maxLen; j > 1; j-- {
if x := entity[entityName[:j]]; x != 0 {
return dst + utf8.EncodeRune(b[dst:], x), src + j + 1
}
}
}
dst1, src1 = dst+i, src+i
copy(b[dst:dst1], b[src:src1])
return dst1, src1
}
// unescape unescapes b's entities in-place, so that "a&lt;b" becomes "a<b".
// attribute should be true if parsing an attribute value.
func unescape(b []byte, attribute bool) []byte {
for i, c := range b {
if c == '&' {
dst, src := unescapeEntity(b, i, i, attribute)
for src < len(b) {
c := b[src]
if c == '&' {
dst, src = unescapeEntity(b, dst, src, attribute)
} else {
b[dst] = c
dst, src = dst+1, src+1
}
}
return b[0:dst]
}
}
return b
}
// lower lower-cases the A-Z bytes in b in-place, so that "aBc" becomes "abc".
func lower(b []byte) []byte {
for i, c := range b {
if 'A' <= c && c <= 'Z' {
b[i] = c + 'a' - 'A'
}
}
return b
}
const escapedChars = "&'<>\"\r"
func escape(w writer, s string) error {
i := strings.IndexAny(s, escapedChars)
for i != -1 {
if _, err := w.WriteString(s[:i]); err != nil {
return err
}
var esc string
switch s[i] {
case '&':
esc = "&amp;"
case '\'':
// "&#39;" is shorter than "&apos;" and apos was not in HTML until HTML5.
esc = "&#39;"
case '<':
esc = "&lt;"
case '>':
esc = "&gt;"
case '"':
// "&#34;" is shorter than "&quot;".
esc = "&#34;"
case '\r':
esc = "&#13;"
default:
panic("unrecognized escape character")
}
s = s[i+1:]
if _, err := w.WriteString(esc); err != nil {
return err
}
i = strings.IndexAny(s, escapedChars)
}
_, err := w.WriteString(s)
return err
}
// EscapeString escapes special characters like "<" to become "&lt;". It
// escapes only five such characters: <, >, &, ' and ".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func EscapeString(s string) string {
if strings.IndexAny(s, escapedChars) == -1 {
return s
}
var buf bytes.Buffer
escape(&buf, s)
return buf.String()
}
// UnescapeString unescapes entities like "&lt;" to become "<". It unescapes a
// larger range of entities than EscapeString escapes. For example, "&aacute;"
// unescapes to "á", as does "&#225;" and "&xE1;".
// UnescapeString(EscapeString(s)) == s always holds, but the converse isn't
// always true.
func UnescapeString(s string) string {
for _, c := range s {
if c == '&' {
return string(unescape([]byte(s), false))
}
}
return s
}

View File

@ -0,0 +1,97 @@
// Copyright 2013 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import "testing"
type unescapeTest struct {
// A short description of the test case.
desc string
// The HTML text.
html string
// The unescaped text.
unescaped string
}
var unescapeTests = []unescapeTest{
// Handle no entities.
{
"copy",
"A\ttext\nstring",
"A\ttext\nstring",
},
// Handle simple named entities.
{
"simple",
"&amp; &gt; &lt;",
"& > <",
},
// Handle hitting the end of the string.
{
"stringEnd",
"&amp &amp",
"& &",
},
// Handle entities with two codepoints.
{
"multiCodepoint",
"text &gesl; blah",
"text \u22db\ufe00 blah",
},
// Handle decimal numeric entities.
{
"decimalEntity",
"Delta = &#916; ",
"Delta = Δ ",
},
// Handle hexadecimal numeric entities.
{
"hexadecimalEntity",
"Lambda = &#x3bb; = &#X3Bb ",
"Lambda = λ = λ ",
},
// Handle numeric early termination.
{
"numericEnds",
"&# &#x &#128;43 &copy = &#169f = &#xa9",
"&# &#x €43 © = ©f = ©",
},
// Handle numeric ISO-8859-1 entity replacements.
{
"numericReplacements",
"Footnote&#x87;",
"Footnote‡",
},
}
func TestUnescape(t *testing.T) {
for _, tt := range unescapeTests {
unescaped := UnescapeString(tt.html)
if unescaped != tt.unescaped {
t.Errorf("TestUnescape %s: want %q, got %q", tt.desc, tt.unescaped, unescaped)
}
}
}
func TestUnescapeEscape(t *testing.T) {
ss := []string{
``,
`abc def`,
`a & b`,
`a&amp;b`,
`a &amp b`,
`&quot;`,
`"`,
`"<&>"`,
`&quot;&lt;&amp;&gt;&quot;`,
`3&5==1 && 0<1, "0&lt;1", a+acute=&aacute;`,
`The special characters are: <, >, &, ' and "`,
}
for _, s := range ss {
if got := UnescapeString(EscapeString(s)); got != s {
t.Errorf("got %q want %q", got, s)
}
}
}

View File

@ -0,0 +1,40 @@
// Copyright 2012 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
// This example demonstrates parsing HTML data and walking the resulting tree.
package html_test
import (
"fmt"
"log"
"strings"
"golang.org/x/net/html"
)
func ExampleParse() {
s := `<p>Links:</p><ul><li><a href="foo">Foo</a><li><a href="/bar/baz">BarBaz</a></ul>`
doc, err := html.Parse(strings.NewReader(s))
if err != nil {
log.Fatal(err)
}
var f func(*html.Node)
f = func(n *html.Node) {
if n.Type == html.ElementNode && n.Data == "a" {
for _, a := range n.Attr {
if a.Key == "href" {
fmt.Println(a.Val)
break
}
}
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
f(c)
}
}
f(doc)
// Output:
// foo
// /bar/baz
}

226
Godeps/_workspace/src/golang.org/x/net/html/foreign.go generated vendored Normal file
View File

@ -0,0 +1,226 @@
// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"strings"
)
func adjustAttributeNames(aa []Attribute, nameMap map[string]string) {
for i := range aa {
if newName, ok := nameMap[aa[i].Key]; ok {
aa[i].Key = newName
}
}
}
func adjustForeignAttributes(aa []Attribute) {
for i, a := range aa {
if a.Key == "" || a.Key[0] != 'x' {
continue
}
switch a.Key {
case "xlink:actuate", "xlink:arcrole", "xlink:href", "xlink:role", "xlink:show",
"xlink:title", "xlink:type", "xml:base", "xml:lang", "xml:space", "xmlns:xlink":
j := strings.Index(a.Key, ":")
aa[i].Namespace = a.Key[:j]
aa[i].Key = a.Key[j+1:]
}
}
}
func htmlIntegrationPoint(n *Node) bool {
if n.Type != ElementNode {
return false
}
switch n.Namespace {
case "math":
if n.Data == "annotation-xml" {
for _, a := range n.Attr {
if a.Key == "encoding" {
val := strings.ToLower(a.Val)
if val == "text/html" || val == "application/xhtml+xml" {
return true
}
}
}
}
case "svg":
switch n.Data {
case "desc", "foreignObject", "title":
return true
}
}
return false
}
func mathMLTextIntegrationPoint(n *Node) bool {
if n.Namespace != "math" {
return false
}
switch n.Data {
case "mi", "mo", "mn", "ms", "mtext":
return true
}
return false
}
// Section 12.2.5.5.
var breakout = map[string]bool{
"b": true,
"big": true,
"blockquote": true,
"body": true,
"br": true,
"center": true,
"code": true,
"dd": true,
"div": true,
"dl": true,
"dt": true,
"em": true,
"embed": true,
"h1": true,
"h2": true,
"h3": true,
"h4": true,
"h5": true,
"h6": true,
"head": true,
"hr": true,
"i": true,
"img": true,
"li": true,
"listing": true,
"menu": true,
"meta": true,
"nobr": true,
"ol": true,
"p": true,
"pre": true,
"ruby": true,
"s": true,
"small": true,
"span": true,
"strong": true,
"strike": true,
"sub": true,
"sup": true,
"table": true,
"tt": true,
"u": true,
"ul": true,
"var": true,
}
// Section 12.2.5.5.
var svgTagNameAdjustments = map[string]string{
"altglyph": "altGlyph",
"altglyphdef": "altGlyphDef",
"altglyphitem": "altGlyphItem",
"animatecolor": "animateColor",
"animatemotion": "animateMotion",
"animatetransform": "animateTransform",
"clippath": "clipPath",
"feblend": "feBlend",
"fecolormatrix": "feColorMatrix",
"fecomponenttransfer": "feComponentTransfer",
"fecomposite": "feComposite",
"feconvolvematrix": "feConvolveMatrix",
"fediffuselighting": "feDiffuseLighting",
"fedisplacementmap": "feDisplacementMap",
"fedistantlight": "feDistantLight",
"feflood": "feFlood",
"fefunca": "feFuncA",
"fefuncb": "feFuncB",
"fefuncg": "feFuncG",
"fefuncr": "feFuncR",
"fegaussianblur": "feGaussianBlur",
"feimage": "feImage",
"femerge": "feMerge",
"femergenode": "feMergeNode",
"femorphology": "feMorphology",
"feoffset": "feOffset",
"fepointlight": "fePointLight",
"fespecularlighting": "feSpecularLighting",
"fespotlight": "feSpotLight",
"fetile": "feTile",
"feturbulence": "feTurbulence",
"foreignobject": "foreignObject",
"glyphref": "glyphRef",
"lineargradient": "linearGradient",
"radialgradient": "radialGradient",
"textpath": "textPath",
}
// Section 12.2.5.1
var mathMLAttributeAdjustments = map[string]string{
"definitionurl": "definitionURL",
}
var svgAttributeAdjustments = map[string]string{
"attributename": "attributeName",
"attributetype": "attributeType",
"basefrequency": "baseFrequency",
"baseprofile": "baseProfile",
"calcmode": "calcMode",
"clippathunits": "clipPathUnits",
"contentscripttype": "contentScriptType",
"contentstyletype": "contentStyleType",
"diffuseconstant": "diffuseConstant",
"edgemode": "edgeMode",
"externalresourcesrequired": "externalResourcesRequired",
"filterres": "filterRes",
"filterunits": "filterUnits",
"glyphref": "glyphRef",
"gradienttransform": "gradientTransform",
"gradientunits": "gradientUnits",
"kernelmatrix": "kernelMatrix",
"kernelunitlength": "kernelUnitLength",
"keypoints": "keyPoints",
"keysplines": "keySplines",
"keytimes": "keyTimes",
"lengthadjust": "lengthAdjust",
"limitingconeangle": "limitingConeAngle",
"markerheight": "markerHeight",
"markerunits": "markerUnits",
"markerwidth": "markerWidth",
"maskcontentunits": "maskContentUnits",
"maskunits": "maskUnits",
"numoctaves": "numOctaves",
"pathlength": "pathLength",
"patterncontentunits": "patternContentUnits",
"patterntransform": "patternTransform",
"patternunits": "patternUnits",
"pointsatx": "pointsAtX",
"pointsaty": "pointsAtY",
"pointsatz": "pointsAtZ",
"preservealpha": "preserveAlpha",
"preserveaspectratio": "preserveAspectRatio",
"primitiveunits": "primitiveUnits",
"refx": "refX",
"refy": "refY",
"repeatcount": "repeatCount",
"repeatdur": "repeatDur",
"requiredextensions": "requiredExtensions",
"requiredfeatures": "requiredFeatures",
"specularconstant": "specularConstant",
"specularexponent": "specularExponent",
"spreadmethod": "spreadMethod",
"startoffset": "startOffset",
"stddeviation": "stdDeviation",
"stitchtiles": "stitchTiles",
"surfacescale": "surfaceScale",
"systemlanguage": "systemLanguage",
"tablevalues": "tableValues",
"targetx": "targetX",
"targety": "targetY",
"textlength": "textLength",
"viewbox": "viewBox",
"viewtarget": "viewTarget",
"xchannelselector": "xChannelSelector",
"ychannelselector": "yChannelSelector",
"zoomandpan": "zoomAndPan",
}

193
Godeps/_workspace/src/golang.org/x/net/html/node.go generated vendored Normal file
View File

@ -0,0 +1,193 @@
// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"golang.org/x/net/html/atom"
)
// A NodeType is the type of a Node.
type NodeType uint32
const (
ErrorNode NodeType = iota
TextNode
DocumentNode
ElementNode
CommentNode
DoctypeNode
scopeMarkerNode
)
// Section 12.2.3.3 says "scope markers are inserted when entering applet
// elements, buttons, object elements, marquees, table cells, and table
// captions, and are used to prevent formatting from 'leaking'".
var scopeMarker = Node{Type: scopeMarkerNode}
// A Node consists of a NodeType and some Data (tag name for element nodes,
// content for text) and are part of a tree of Nodes. Element nodes may also
// have a Namespace and contain a slice of Attributes. Data is unescaped, so
// that it looks like "a<b" rather than "a&lt;b". For element nodes, DataAtom
// is the atom for Data, or zero if Data is not a known tag name.
//
// An empty Namespace implies a "http://www.w3.org/1999/xhtml" namespace.
// Similarly, "math" is short for "http://www.w3.org/1998/Math/MathML", and
// "svg" is short for "http://www.w3.org/2000/svg".
type Node struct {
Parent, FirstChild, LastChild, PrevSibling, NextSibling *Node
Type NodeType
DataAtom atom.Atom
Data string
Namespace string
Attr []Attribute
}
// InsertBefore inserts newChild as a child of n, immediately before oldChild
// in the sequence of n's children. oldChild may be nil, in which case newChild
// is appended to the end of n's children.
//
// It will panic if newChild already has a parent or siblings.
func (n *Node) InsertBefore(newChild, oldChild *Node) {
if newChild.Parent != nil || newChild.PrevSibling != nil || newChild.NextSibling != nil {
panic("html: InsertBefore called for an attached child Node")
}
var prev, next *Node
if oldChild != nil {
prev, next = oldChild.PrevSibling, oldChild
} else {
prev = n.LastChild
}
if prev != nil {
prev.NextSibling = newChild
} else {
n.FirstChild = newChild
}
if next != nil {
next.PrevSibling = newChild
} else {
n.LastChild = newChild
}
newChild.Parent = n
newChild.PrevSibling = prev
newChild.NextSibling = next
}
// AppendChild adds a node c as a child of n.
//
// It will panic if c already has a parent or siblings.
func (n *Node) AppendChild(c *Node) {
if c.Parent != nil || c.PrevSibling != nil || c.NextSibling != nil {
panic("html: AppendChild called for an attached child Node")
}
last := n.LastChild
if last != nil {
last.NextSibling = c
} else {
n.FirstChild = c
}
n.LastChild = c
c.Parent = n
c.PrevSibling = last
}
// RemoveChild removes a node c that is a child of n. Afterwards, c will have
// no parent and no siblings.
//
// It will panic if c's parent is not n.
func (n *Node) RemoveChild(c *Node) {
if c.Parent != n {
panic("html: RemoveChild called for a non-child Node")
}
if n.FirstChild == c {
n.FirstChild = c.NextSibling
}
if c.NextSibling != nil {
c.NextSibling.PrevSibling = c.PrevSibling
}
if n.LastChild == c {
n.LastChild = c.PrevSibling
}
if c.PrevSibling != nil {
c.PrevSibling.NextSibling = c.NextSibling
}
c.Parent = nil
c.PrevSibling = nil
c.NextSibling = nil
}
// reparentChildren reparents all of src's child nodes to dst.
func reparentChildren(dst, src *Node) {
for {
child := src.FirstChild
if child == nil {
break
}
src.RemoveChild(child)
dst.AppendChild(child)
}
}
// clone returns a new node with the same type, data and attributes.
// The clone has no parent, no siblings and no children.
func (n *Node) clone() *Node {
m := &Node{
Type: n.Type,
DataAtom: n.DataAtom,
Data: n.Data,
Attr: make([]Attribute, len(n.Attr)),
}
copy(m.Attr, n.Attr)
return m
}
// nodeStack is a stack of nodes.
type nodeStack []*Node
// pop pops the stack. It will panic if s is empty.
func (s *nodeStack) pop() *Node {
i := len(*s)
n := (*s)[i-1]
*s = (*s)[:i-1]
return n
}
// top returns the most recently pushed node, or nil if s is empty.
func (s *nodeStack) top() *Node {
if i := len(*s); i > 0 {
return (*s)[i-1]
}
return nil
}
// index returns the index of the top-most occurrence of n in the stack, or -1
// if n is not present.
func (s *nodeStack) index(n *Node) int {
for i := len(*s) - 1; i >= 0; i-- {
if (*s)[i] == n {
return i
}
}
return -1
}
// insert inserts a node at the given index.
func (s *nodeStack) insert(i int, n *Node) {
(*s) = append(*s, nil)
copy((*s)[i+1:], (*s)[i:])
(*s)[i] = n
}
// remove removes a node from the stack. It is a no-op if n is not present.
func (s *nodeStack) remove(n *Node) {
i := s.index(n)
if i == -1 {
return
}
copy((*s)[i:], (*s)[i+1:])
j := len(*s) - 1
(*s)[j] = nil
*s = (*s)[:j]
}

View File

@ -0,0 +1,146 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"fmt"
)
// checkTreeConsistency checks that a node and its descendants are all
// consistent in their parent/child/sibling relationships.
func checkTreeConsistency(n *Node) error {
return checkTreeConsistency1(n, 0)
}
func checkTreeConsistency1(n *Node, depth int) error {
if depth == 1e4 {
return fmt.Errorf("html: tree looks like it contains a cycle")
}
if err := checkNodeConsistency(n); err != nil {
return err
}
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := checkTreeConsistency1(c, depth+1); err != nil {
return err
}
}
return nil
}
// checkNodeConsistency checks that a node's parent/child/sibling relationships
// are consistent.
func checkNodeConsistency(n *Node) error {
if n == nil {
return nil
}
nParent := 0
for p := n.Parent; p != nil; p = p.Parent {
nParent++
if nParent == 1e4 {
return fmt.Errorf("html: parent list looks like an infinite loop")
}
}
nForward := 0
for c := n.FirstChild; c != nil; c = c.NextSibling {
nForward++
if nForward == 1e6 {
return fmt.Errorf("html: forward list of children looks like an infinite loop")
}
if c.Parent != n {
return fmt.Errorf("html: inconsistent child/parent relationship")
}
}
nBackward := 0
for c := n.LastChild; c != nil; c = c.PrevSibling {
nBackward++
if nBackward == 1e6 {
return fmt.Errorf("html: backward list of children looks like an infinite loop")
}
if c.Parent != n {
return fmt.Errorf("html: inconsistent child/parent relationship")
}
}
if n.Parent != nil {
if n.Parent == n {
return fmt.Errorf("html: inconsistent parent relationship")
}
if n.Parent == n.FirstChild {
return fmt.Errorf("html: inconsistent parent/first relationship")
}
if n.Parent == n.LastChild {
return fmt.Errorf("html: inconsistent parent/last relationship")
}
if n.Parent == n.PrevSibling {
return fmt.Errorf("html: inconsistent parent/prev relationship")
}
if n.Parent == n.NextSibling {
return fmt.Errorf("html: inconsistent parent/next relationship")
}
parentHasNAsAChild := false
for c := n.Parent.FirstChild; c != nil; c = c.NextSibling {
if c == n {
parentHasNAsAChild = true
break
}
}
if !parentHasNAsAChild {
return fmt.Errorf("html: inconsistent parent/child relationship")
}
}
if n.PrevSibling != nil && n.PrevSibling.NextSibling != n {
return fmt.Errorf("html: inconsistent prev/next relationship")
}
if n.NextSibling != nil && n.NextSibling.PrevSibling != n {
return fmt.Errorf("html: inconsistent next/prev relationship")
}
if (n.FirstChild == nil) != (n.LastChild == nil) {
return fmt.Errorf("html: inconsistent first/last relationship")
}
if n.FirstChild != nil && n.FirstChild == n.LastChild {
// We have a sole child.
if n.FirstChild.PrevSibling != nil || n.FirstChild.NextSibling != nil {
return fmt.Errorf("html: inconsistent sole child's sibling relationship")
}
}
seen := map[*Node]bool{}
var last *Node
for c := n.FirstChild; c != nil; c = c.NextSibling {
if seen[c] {
return fmt.Errorf("html: inconsistent repeated child")
}
seen[c] = true
last = c
}
if last != n.LastChild {
return fmt.Errorf("html: inconsistent last relationship")
}
var first *Node
for c := n.LastChild; c != nil; c = c.PrevSibling {
if !seen[c] {
return fmt.Errorf("html: inconsistent missing child")
}
delete(seen, c)
first = c
}
if first != n.FirstChild {
return fmt.Errorf("html: inconsistent first relationship")
}
if len(seen) != 0 {
return fmt.Errorf("html: inconsistent forwards/backwards child list")
}
return nil
}

2094
Godeps/_workspace/src/golang.org/x/net/html/parse.go generated vendored Normal file

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,388 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"bufio"
"bytes"
"errors"
"fmt"
"io"
"io/ioutil"
"os"
"path/filepath"
"runtime"
"sort"
"strings"
"testing"
"golang.org/x/net/html/atom"
)
// readParseTest reads a single test case from r.
func readParseTest(r *bufio.Reader) (text, want, context string, err error) {
line, err := r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
var b []byte
// Read the HTML.
if string(line) != "#data\n" {
return "", "", "", fmt.Errorf(`got %q want "#data\n"`, line)
}
for {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
if line[0] == '#' {
break
}
b = append(b, line...)
}
text = strings.TrimSuffix(string(b), "\n")
b = b[:0]
// Skip the error list.
if string(line) != "#errors\n" {
return "", "", "", fmt.Errorf(`got %q want "#errors\n"`, line)
}
for {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
if line[0] == '#' {
break
}
}
if string(line) == "#document-fragment\n" {
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
context = strings.TrimSpace(string(line))
line, err = r.ReadSlice('\n')
if err != nil {
return "", "", "", err
}
}
// Read the dump of what the parse tree should be.
if string(line) != "#document\n" {
return "", "", "", fmt.Errorf(`got %q want "#document\n"`, line)
}
inQuote := false
for {
line, err = r.ReadSlice('\n')
if err != nil && err != io.EOF {
return "", "", "", err
}
trimmed := bytes.Trim(line, "| \n")
if len(trimmed) > 0 {
if line[0] == '|' && trimmed[0] == '"' {
inQuote = true
}
if trimmed[len(trimmed)-1] == '"' && !(line[0] == '|' && len(trimmed) == 1) {
inQuote = false
}
}
if len(line) == 0 || len(line) == 1 && line[0] == '\n' && !inQuote {
break
}
b = append(b, line...)
}
return text, string(b), context, nil
}
func dumpIndent(w io.Writer, level int) {
io.WriteString(w, "| ")
for i := 0; i < level; i++ {
io.WriteString(w, " ")
}
}
type sortedAttributes []Attribute
func (a sortedAttributes) Len() int {
return len(a)
}
func (a sortedAttributes) Less(i, j int) bool {
if a[i].Namespace != a[j].Namespace {
return a[i].Namespace < a[j].Namespace
}
return a[i].Key < a[j].Key
}
func (a sortedAttributes) Swap(i, j int) {
a[i], a[j] = a[j], a[i]
}
func dumpLevel(w io.Writer, n *Node, level int) error {
dumpIndent(w, level)
switch n.Type {
case ErrorNode:
return errors.New("unexpected ErrorNode")
case DocumentNode:
return errors.New("unexpected DocumentNode")
case ElementNode:
if n.Namespace != "" {
fmt.Fprintf(w, "<%s %s>", n.Namespace, n.Data)
} else {
fmt.Fprintf(w, "<%s>", n.Data)
}
attr := sortedAttributes(n.Attr)
sort.Sort(attr)
for _, a := range attr {
io.WriteString(w, "\n")
dumpIndent(w, level+1)
if a.Namespace != "" {
fmt.Fprintf(w, `%s %s="%s"`, a.Namespace, a.Key, a.Val)
} else {
fmt.Fprintf(w, `%s="%s"`, a.Key, a.Val)
}
}
case TextNode:
fmt.Fprintf(w, `"%s"`, n.Data)
case CommentNode:
fmt.Fprintf(w, "<!-- %s -->", n.Data)
case DoctypeNode:
fmt.Fprintf(w, "<!DOCTYPE %s", n.Data)
if n.Attr != nil {
var p, s string
for _, a := range n.Attr {
switch a.Key {
case "public":
p = a.Val
case "system":
s = a.Val
}
}
if p != "" || s != "" {
fmt.Fprintf(w, ` "%s"`, p)
fmt.Fprintf(w, ` "%s"`, s)
}
}
io.WriteString(w, ">")
case scopeMarkerNode:
return errors.New("unexpected scopeMarkerNode")
default:
return errors.New("unknown node type")
}
io.WriteString(w, "\n")
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := dumpLevel(w, c, level+1); err != nil {
return err
}
}
return nil
}
func dump(n *Node) (string, error) {
if n == nil || n.FirstChild == nil {
return "", nil
}
var b bytes.Buffer
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := dumpLevel(&b, c, 0); err != nil {
return "", err
}
}
return b.String(), nil
}
const testDataDir = "testdata/webkit/"
func TestParser(t *testing.T) {
testFiles, err := filepath.Glob(testDataDir + "*.dat")
if err != nil {
t.Fatal(err)
}
for _, tf := range testFiles {
f, err := os.Open(tf)
if err != nil {
t.Fatal(err)
}
defer f.Close()
r := bufio.NewReader(f)
for i := 0; ; i++ {
text, want, context, err := readParseTest(r)
if err == io.EOF {
break
}
if err != nil {
t.Fatal(err)
}
err = testParseCase(text, want, context)
if err != nil {
t.Errorf("%s test #%d %q, %s", tf, i, text, err)
}
}
}
}
// testParseCase tests one test case from the test files. If the test does not
// pass, it returns an error that explains the failure.
// text is the HTML to be parsed, want is a dump of the correct parse tree,
// and context is the name of the context node, if any.
func testParseCase(text, want, context string) (err error) {
defer func() {
if x := recover(); x != nil {
switch e := x.(type) {
case error:
err = e
default:
err = fmt.Errorf("%v", e)
}
}
}()
var doc *Node
if context == "" {
doc, err = Parse(strings.NewReader(text))
if err != nil {
return err
}
} else {
contextNode := &Node{
Type: ElementNode,
DataAtom: atom.Lookup([]byte(context)),
Data: context,
}
nodes, err := ParseFragment(strings.NewReader(text), contextNode)
if err != nil {
return err
}
doc = &Node{
Type: DocumentNode,
}
for _, n := range nodes {
doc.AppendChild(n)
}
}
if err := checkTreeConsistency(doc); err != nil {
return err
}
got, err := dump(doc)
if err != nil {
return err
}
// Compare the parsed tree to the #document section.
if got != want {
return fmt.Errorf("got vs want:\n----\n%s----\n%s----", got, want)
}
if renderTestBlacklist[text] || context != "" {
return nil
}
// Check that rendering and re-parsing results in an identical tree.
pr, pw := io.Pipe()
go func() {
pw.CloseWithError(Render(pw, doc))
}()
doc1, err := Parse(pr)
if err != nil {
return err
}
got1, err := dump(doc1)
if err != nil {
return err
}
if got != got1 {
return fmt.Errorf("got vs got1:\n----\n%s----\n%s----", got, got1)
}
return nil
}
// Some test input result in parse trees are not 'well-formed' despite
// following the HTML5 recovery algorithms. Rendering and re-parsing such a
// tree will not result in an exact clone of that tree. We blacklist such
// inputs from the render test.
var renderTestBlacklist = map[string]bool{
// The second <a> will be reparented to the first <table>'s parent. This
// results in an <a> whose parent is an <a>, which is not 'well-formed'.
`<a><table><td><a><table></table><a></tr><a></table><b>X</b>C<a>Y`: true,
// The same thing with a <p>:
`<p><table></p>`: true,
// More cases of <a> being reparented:
`<a href="blah">aba<table><a href="foo">br<tr><td></td></tr>x</table>aoe`: true,
`<a><table><a></table><p><a><div><a>`: true,
`<a><table><td><a><table></table><a></tr><a></table><a>`: true,
// A similar reparenting situation involving <nobr>:
`<!DOCTYPE html><body><b><nobr>1<table><nobr></b><i><nobr>2<nobr></i>3`: true,
// A <plaintext> element is reparented, putting it before a table.
// A <plaintext> element can't have anything after it in HTML.
`<table><plaintext><td>`: true,
`<!doctype html><table><plaintext></plaintext>`: true,
`<!doctype html><table><tbody><plaintext></plaintext>`: true,
`<!doctype html><table><tbody><tr><plaintext></plaintext>`: true,
// A form inside a table inside a form doesn't work either.
`<!doctype html><form><table></form><form></table></form>`: true,
// A script that ends at EOF may escape its own closing tag when rendered.
`<!doctype html><script><!--<script `: true,
`<!doctype html><script><!--<script <`: true,
`<!doctype html><script><!--<script <a`: true,
`<!doctype html><script><!--<script </`: true,
`<!doctype html><script><!--<script </s`: true,
`<!doctype html><script><!--<script </script`: true,
`<!doctype html><script><!--<script </scripta`: true,
`<!doctype html><script><!--<script -`: true,
`<!doctype html><script><!--<script -a`: true,
`<!doctype html><script><!--<script -<`: true,
`<!doctype html><script><!--<script --`: true,
`<!doctype html><script><!--<script --a`: true,
`<!doctype html><script><!--<script --<`: true,
`<script><!--<script `: true,
`<script><!--<script <a`: true,
`<script><!--<script </script`: true,
`<script><!--<script </scripta`: true,
`<script><!--<script -`: true,
`<script><!--<script -a`: true,
`<script><!--<script --`: true,
`<script><!--<script --a`: true,
`<script><!--<script <`: true,
`<script><!--<script </`: true,
`<script><!--<script </s`: true,
// Reconstructing the active formatting elements results in a <plaintext>
// element that contains an <a> element.
`<!doctype html><p><a><plaintext>b`: true,
}
func TestNodeConsistency(t *testing.T) {
// inconsistentNode is a Node whose DataAtom and Data do not agree.
inconsistentNode := &Node{
Type: ElementNode,
DataAtom: atom.Frameset,
Data: "table",
}
_, err := ParseFragment(strings.NewReader("<p>hello</p>"), inconsistentNode)
if err == nil {
t.Errorf("got nil error, want non-nil")
}
}
func BenchmarkParser(b *testing.B) {
buf, err := ioutil.ReadFile("testdata/go1.html")
if err != nil {
b.Fatalf("could not read testdata/go1.html: %v", err)
}
b.SetBytes(int64(len(buf)))
runtime.GC()
b.ReportAllocs()
b.ResetTimer()
for i := 0; i < b.N; i++ {
Parse(bytes.NewBuffer(buf))
}
}

271
Godeps/_workspace/src/golang.org/x/net/html/render.go generated vendored Normal file
View File

@ -0,0 +1,271 @@
// Copyright 2011 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"bufio"
"errors"
"fmt"
"io"
"strings"
)
type writer interface {
io.Writer
WriteByte(c byte) error // in Go 1.1, use io.ByteWriter
WriteString(string) (int, error)
}
// Render renders the parse tree n to the given writer.
//
// Rendering is done on a 'best effort' basis: calling Parse on the output of
// Render will always result in something similar to the original tree, but it
// is not necessarily an exact clone unless the original tree was 'well-formed'.
// 'Well-formed' is not easily specified; the HTML5 specification is
// complicated.
//
// Calling Parse on arbitrary input typically results in a 'well-formed' parse
// tree. However, it is possible for Parse to yield a 'badly-formed' parse tree.
// For example, in a 'well-formed' parse tree, no <a> element is a child of
// another <a> element: parsing "<a><a>" results in two sibling elements.
// Similarly, in a 'well-formed' parse tree, no <a> element is a child of a
// <table> element: parsing "<p><table><a>" results in a <p> with two sibling
// children; the <a> is reparented to the <table>'s parent. However, calling
// Parse on "<a><table><a>" does not return an error, but the result has an <a>
// element with an <a> child, and is therefore not 'well-formed'.
//
// Programmatically constructed trees are typically also 'well-formed', but it
// is possible to construct a tree that looks innocuous but, when rendered and
// re-parsed, results in a different tree. A simple example is that a solitary
// text node would become a tree containing <html>, <head> and <body> elements.
// Another example is that the programmatic equivalent of "a<head>b</head>c"
// becomes "<html><head><head/><body>abc</body></html>".
func Render(w io.Writer, n *Node) error {
if x, ok := w.(writer); ok {
return render(x, n)
}
buf := bufio.NewWriter(w)
if err := render(buf, n); err != nil {
return err
}
return buf.Flush()
}
// plaintextAbort is returned from render1 when a <plaintext> element
// has been rendered. No more end tags should be rendered after that.
var plaintextAbort = errors.New("html: internal error (plaintext abort)")
func render(w writer, n *Node) error {
err := render1(w, n)
if err == plaintextAbort {
err = nil
}
return err
}
func render1(w writer, n *Node) error {
// Render non-element nodes; these are the easy cases.
switch n.Type {
case ErrorNode:
return errors.New("html: cannot render an ErrorNode node")
case TextNode:
return escape(w, n.Data)
case DocumentNode:
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := render1(w, c); err != nil {
return err
}
}
return nil
case ElementNode:
// No-op.
case CommentNode:
if _, err := w.WriteString("<!--"); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
if _, err := w.WriteString("-->"); err != nil {
return err
}
return nil
case DoctypeNode:
if _, err := w.WriteString("<!DOCTYPE "); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
if n.Attr != nil {
var p, s string
for _, a := range n.Attr {
switch a.Key {
case "public":
p = a.Val
case "system":
s = a.Val
}
}
if p != "" {
if _, err := w.WriteString(" PUBLIC "); err != nil {
return err
}
if err := writeQuoted(w, p); err != nil {
return err
}
if s != "" {
if err := w.WriteByte(' '); err != nil {
return err
}
if err := writeQuoted(w, s); err != nil {
return err
}
}
} else if s != "" {
if _, err := w.WriteString(" SYSTEM "); err != nil {
return err
}
if err := writeQuoted(w, s); err != nil {
return err
}
}
}
return w.WriteByte('>')
default:
return errors.New("html: unknown node type")
}
// Render the <xxx> opening tag.
if err := w.WriteByte('<'); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
for _, a := range n.Attr {
if err := w.WriteByte(' '); err != nil {
return err
}
if a.Namespace != "" {
if _, err := w.WriteString(a.Namespace); err != nil {
return err
}
if err := w.WriteByte(':'); err != nil {
return err
}
}
if _, err := w.WriteString(a.Key); err != nil {
return err
}
if _, err := w.WriteString(`="`); err != nil {
return err
}
if err := escape(w, a.Val); err != nil {
return err
}
if err := w.WriteByte('"'); err != nil {
return err
}
}
if voidElements[n.Data] {
if n.FirstChild != nil {
return fmt.Errorf("html: void element <%s> has child nodes", n.Data)
}
_, err := w.WriteString("/>")
return err
}
if err := w.WriteByte('>'); err != nil {
return err
}
// Add initial newline where there is danger of a newline beging ignored.
if c := n.FirstChild; c != nil && c.Type == TextNode && strings.HasPrefix(c.Data, "\n") {
switch n.Data {
case "pre", "listing", "textarea":
if err := w.WriteByte('\n'); err != nil {
return err
}
}
}
// Render any child nodes.
switch n.Data {
case "iframe", "noembed", "noframes", "noscript", "plaintext", "script", "style", "xmp":
for c := n.FirstChild; c != nil; c = c.NextSibling {
if c.Type == TextNode {
if _, err := w.WriteString(c.Data); err != nil {
return err
}
} else {
if err := render1(w, c); err != nil {
return err
}
}
}
if n.Data == "plaintext" {
// Don't render anything else. <plaintext> must be the
// last element in the file, with no closing tag.
return plaintextAbort
}
default:
for c := n.FirstChild; c != nil; c = c.NextSibling {
if err := render1(w, c); err != nil {
return err
}
}
}
// Render the </xxx> closing tag.
if _, err := w.WriteString("</"); err != nil {
return err
}
if _, err := w.WriteString(n.Data); err != nil {
return err
}
return w.WriteByte('>')
}
// writeQuoted writes s to w surrounded by quotes. Normally it will use double
// quotes, but if s contains a double quote, it will use single quotes.
// It is used for writing the identifiers in a doctype declaration.
// In valid HTML, they can't contain both types of quotes.
func writeQuoted(w writer, s string) error {
var q byte = '"'
if strings.Contains(s, `"`) {
q = '\''
}
if err := w.WriteByte(q); err != nil {
return err
}
if _, err := w.WriteString(s); err != nil {
return err
}
if err := w.WriteByte(q); err != nil {
return err
}
return nil
}
// Section 12.1.2, "Elements", gives this list of void elements. Void elements
// are those that can't have any contents.
var voidElements = map[string]bool{
"area": true,
"base": true,
"br": true,
"col": true,
"command": true,
"embed": true,
"hr": true,
"img": true,
"input": true,
"keygen": true,
"link": true,
"meta": true,
"param": true,
"source": true,
"track": true,
"wbr": true,
}

View File

@ -0,0 +1,156 @@
// Copyright 2010 The Go Authors. All rights reserved.
// Use of this source code is governed by a BSD-style
// license that can be found in the LICENSE file.
package html
import (
"bytes"
"testing"
)
func TestRenderer(t *testing.T) {
nodes := [...]*Node{
0: {
Type: ElementNode,
Data: "html",
},
1: {
Type: ElementNode,
Data: "head",
},
2: {
Type: ElementNode,
Data: "body",
},
3: {
Type: TextNode,
Data: "0<1",
},
4: {
Type: ElementNode,
Data: "p",
Attr: []Attribute{
{
Key: "id",
Val: "A",
},
{
Key: "foo",
Val: `abc"def`,
},
},
},
5: {
Type: TextNode,
Data: "2",
},
6: {
Type: ElementNode,
Data: "b",
Attr: []Attribute{
{
Key: "empty",
Val: "",
},
},
},
7: {
Type: TextNode,
Data: "3",
},
8: {
Type: ElementNode,
Data: "i",
Attr: []Attribute{
{
Key: "backslash",
Val: `\`,
},
},
},
9: {
Type: TextNode,
Data: "&4",
},
10: {
Type: TextNode,
Data: "5",
},
11: {
Type: ElementNode,
Data: "blockquote",
},
12: {
Type: ElementNode,
Data: "br",
},
13: {
Type: TextNode,
Data: "6",
},
}
// Build a tree out of those nodes, based on a textual representation.
// Only the ".\t"s are significant. The trailing HTML-like text is
// just commentary. The "0:" prefixes are for easy cross-reference with
// the nodes array.
treeAsText := [...]string{
0: `<html>`,
1: `. <head>`,
2: `. <body>`,
3: `. . "0&lt;1"`,
4: `. . <p id="A" foo="abc&#34;def">`,
5: `. . . "2"`,
6: `. . . <b empty="">`,
7: `. . . . "3"`,
8: `. . . <i backslash="\">`,
9: `. . . . "&amp;4"`,
10: `. . "5"`,
11: `. . <blockquote>`,
12: `. . <br>`,
13: `. . "6"`,
}
if len(nodes) != len(treeAsText) {
t.Fatal("len(nodes) != len(treeAsText)")
}
var stack [8]*Node
for i, line := range treeAsText {
level := 0
for line[0] == '.' {
// Strip a leading ".\t".
line = line[2:]
level++
}
n := nodes[i]
if level == 0 {
if stack[0] != nil {
t.Fatal("multiple root nodes")
}
stack[0] = n
} else {
stack[level-1].AppendChild(n)
stack[level] = n
for i := level + 1; i < len(stack); i++ {
stack[i] = nil
}
}
// At each stage of tree construction, we check all nodes for consistency.
for j, m := range nodes {
if err := checkNodeConsistency(m); err != nil {
t.Fatalf("i=%d, j=%d: %v", i, j, err)
}
}
}
want := `<html><head></head><body>0&lt;1<p id="A" foo="abc&#34;def">` +
`2<b empty="">3</b><i backslash="\">&amp;4</i></p>` +
`5<blockquote></blockquote><br/>6</body></html>`
b := new(bytes.Buffer)
if err := Render(b, nodes[0]); err != nil {
t.Fatal(err)
}
if got := b.String(); got != want {
t.Errorf("got vs want:\n%s\n%s\n", got, want)
}
}

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,28 @@
The *.dat files in this directory are copied from The WebKit Open Source
Project, specifically $WEBKITROOT/LayoutTests/html5lib/resources.
WebKit is licensed under a BSD style license.
http://webkit.org/coding/bsd-license.html says:
Copyright (C) 2009 Apple Inc. All rights reserved.
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
1. Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
2. Redistributions in binary form must reproduce the above copyright notice,
this list of conditions and the following disclaimer in the documentation
and/or other materials provided with the distribution.
THIS SOFTWARE IS PROVIDED BY APPLE INC. AND ITS CONTRIBUTORS "AS IS" AND ANY
EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL APPLE INC. OR ITS CONTRIBUTORS BE LIABLE FOR ANY
DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
(INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

View File

@ -0,0 +1,194 @@
#data
<a><p></a></p>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <p>
| <a>
#data
<a>1<p>2</a>3</p>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <p>
| <a>
| "2"
| "3"
#data
<a>1<button>2</a>3</button>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <button>
| <a>
| "2"
| "3"
#data
<a>1<b>2</a>3</b>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <b>
| "2"
| <b>
| "3"
#data
<a>1<div>2<div>3</a>4</div>5</div>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <div>
| <a>
| "2"
| <div>
| <a>
| "3"
| "4"
| "5"
#data
<table><a>1<p>2</a>3</p>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <p>
| <a>
| "2"
| "3"
| <table>
#data
<b><b><a><p></a>
#errors
#document
| <html>
| <head>
| <body>
| <b>
| <b>
| <a>
| <p>
| <a>
#data
<b><a><b><p></a>
#errors
#document
| <html>
| <head>
| <body>
| <b>
| <a>
| <b>
| <b>
| <p>
| <a>
#data
<a><b><b><p></a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <b>
| <b>
| <b>
| <b>
| <p>
| <a>
#data
<p>1<s id="A">2<b id="B">3</p>4</s>5</b>
#errors
#document
| <html>
| <head>
| <body>
| <p>
| "1"
| <s>
| id="A"
| "2"
| <b>
| id="B"
| "3"
| <s>
| id="A"
| <b>
| id="B"
| "4"
| <b>
| id="B"
| "5"
#data
<table><a>1<td>2</td>3</table>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| "1"
| <a>
| "3"
| <table>
| <tbody>
| <tr>
| <td>
| "2"
#data
<table>A<td>B</td>C</table>
#errors
#document
| <html>
| <head>
| <body>
| "AC"
| <table>
| <tbody>
| <tr>
| <td>
| "B"
#data
<a><svg><tr><input></a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <svg svg>
| <svg tr>
| <svg input>

View File

@ -0,0 +1,31 @@
#data
<b>1<i>2<p>3</b>4
#errors
#document
| <html>
| <head>
| <body>
| <b>
| "1"
| <i>
| "2"
| <i>
| <p>
| <b>
| "3"
| "4"
#data
<a><div><style></style><address><a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <div>
| <a>
| <style>
| <address>
| <a>
| <a>

View File

@ -0,0 +1,135 @@
#data
FOO<!-- BAR -->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -->
| "BAZ"
#data
FOO<!-- BAR --!>BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -->
| "BAZ"
#data
FOO<!-- BAR -- >BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -- >BAZ -->
#data
FOO<!-- BAR -- <QUX> -- MUX -->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -- <QUX> -- MUX -->
| "BAZ"
#data
FOO<!-- BAR -- <QUX> -- MUX --!>BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -- <QUX> -- MUX -->
| "BAZ"
#data
FOO<!-- BAR -- <QUX> -- MUX -- >BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- BAR -- <QUX> -- MUX -- >BAZ -->
#data
FOO<!---->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- -->
| "BAZ"
#data
FOO<!--->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- -->
| "BAZ"
#data
FOO<!-->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- -->
| "BAZ"
#data
<?xml version="1.0">Hi
#errors
#document
| <!-- ?xml version="1.0" -->
| <html>
| <head>
| <body>
| "Hi"
#data
<?xml version="1.0">
#errors
#document
| <!-- ?xml version="1.0" -->
| <html>
| <head>
| <body>
#data
<?xml version
#errors
#document
| <!-- ?xml version -->
| <html>
| <head>
| <body>
#data
FOO<!----->BAZ
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <!-- - -->
| "BAZ"

View File

@ -0,0 +1,370 @@
#data
<!DOCTYPE html>Hello
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "Hello"
#data
<!dOctYpE HtMl>Hello
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPEhtml>Hello
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE>Hello
#errors
#document
| <!DOCTYPE >
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE >Hello
#errors
#document
| <!DOCTYPE >
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato >Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato taco>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato taco "ddd>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato sYstEM>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato sYstEM >Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato sYstEM ggg>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato SYSTEM taco >Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato SYSTEM 'taco"'>Hello
#errors
#document
| <!DOCTYPE potato "" "taco"">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato SYSTEM "taco">Hello
#errors
#document
| <!DOCTYPE potato "" "taco">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato SYSTEM "tai'co">Hello
#errors
#document
| <!DOCTYPE potato "" "tai'co">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato SYSTEMtaco "ddd">Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato grass SYSTEM taco>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato pUbLIc>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato pUbLIc >Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato pUbLIcgoof>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato PUBLIC goof>Hello
#errors
#document
| <!DOCTYPE potato>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato PUBLIC "go'of">Hello
#errors
#document
| <!DOCTYPE potato "go'of" "">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato PUBLIC 'go'of'>Hello
#errors
#document
| <!DOCTYPE potato "go" "">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato PUBLIC 'go:hh of' >Hello
#errors
#document
| <!DOCTYPE potato "go:hh of" "">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE potato PUBLIC "W3C-//dfdf" SYSTEM ggg>Hello
#errors
#document
| <!DOCTYPE potato "W3C-//dfdf" "">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"
"http://www.w3.org/TR/html4/strict.dtd">Hello
#errors
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE ...>Hello
#errors
#document
| <!DOCTYPE ...>
| <html>
| <head>
| <body>
| "Hello"
#data
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
#errors
#document
| <!DOCTYPE html "-//W3C//DTD XHTML 1.0 Transitional//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Frameset//EN"
"http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd">
#errors
#document
| <!DOCTYPE html "-//W3C//DTD XHTML 1.0 Frameset//EN" "http://www.w3.org/TR/xhtml1/DTD/xhtml1-frameset.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE root-element [SYSTEM OR PUBLIC FPI] "uri" [
<!-- internal declarations -->
]>
#errors
#document
| <!DOCTYPE root-element>
| <html>
| <head>
| <body>
| "]>"
#data
<!DOCTYPE html PUBLIC
"-//WAPFORUM//DTD XHTML Mobile 1.0//EN"
"http://www.wapforum.org/DTD/xhtml-mobile10.dtd">
#errors
#document
| <!DOCTYPE html "-//WAPFORUM//DTD XHTML Mobile 1.0//EN" "http://www.wapforum.org/DTD/xhtml-mobile10.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE HTML SYSTEM "http://www.w3.org/DTD/HTML4-strict.dtd"><body><b>Mine!</b></body>
#errors
#document
| <!DOCTYPE html "" "http://www.w3.org/DTD/HTML4-strict.dtd">
| <html>
| <head>
| <body>
| <b>
| "Mine!"
#data
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN""http://www.w3.org/TR/html4/strict.dtd">
#errors
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01//EN"'http://www.w3.org/TR/html4/strict.dtd'>
#errors
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE HTML PUBLIC"-//W3C//DTD HTML 4.01//EN"'http://www.w3.org/TR/html4/strict.dtd'>
#errors
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
| <html>
| <head>
| <body>
#data
<!DOCTYPE HTML PUBLIC'-//W3C//DTD HTML 4.01//EN''http://www.w3.org/TR/html4/strict.dtd'>
#errors
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "http://www.w3.org/TR/html4/strict.dtd">
| <html>
| <head>
| <body>

View File

@ -0,0 +1,603 @@
#data
FOO&gt;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO>BAR"
#data
FOO&gtBAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO>BAR"
#data
FOO&gt BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO> BAR"
#data
FOO&gt;;;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO>;;BAR"
#data
I'm &notit; I tell you
#errors
#document
| <html>
| <head>
| <body>
| "I'm ¬it; I tell you"
#data
I'm &notin; I tell you
#errors
#document
| <html>
| <head>
| <body>
| "I'm ∉ I tell you"
#data
FOO& BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO& BAR"
#data
FOO&<BAR>
#errors
#document
| <html>
| <head>
| <body>
| "FOO&"
| <bar>
#data
FOO&&&&gt;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO&&&>BAR"
#data
FOO&#41;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO)BAR"
#data
FOO&#x41;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOOABAR"
#data
FOO&#X41;BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOOABAR"
#data
FOO&#BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO&#BAR"
#data
FOO&#ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO&#ZOO"
#data
FOO&#xBAR
#errors
#document
| <html>
| <head>
| <body>
| "FOOºR"
#data
FOO&#xZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO&#xZOO"
#data
FOO&#XZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO&#XZOO"
#data
FOO&#41BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO)BAR"
#data
FOO&#x41BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO䆺R"
#data
FOO&#x41ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOAZOO"
#data
FOO&#x0000;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#x0078;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOxZOO"
#data
FOO&#x0079;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOyZOO"
#data
FOO&#x0080;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO€ZOO"
#data
FOO&#x0081;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0082;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0083;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOƒZOO"
#data
FOO&#x0084;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO„ZOO"
#data
FOO&#x0085;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO…ZOO"
#data
FOO&#x0086;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO†ZOO"
#data
FOO&#x0087;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO‡ZOO"
#data
FOO&#x0088;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOˆZOO"
#data
FOO&#x0089;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO‰ZOO"
#data
FOO&#x008A;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOŠZOO"
#data
FOO&#x008B;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x008C;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOŒZOO"
#data
FOO&#x008D;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x008E;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOŽZOO"
#data
FOO&#x008F;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0090;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0091;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0092;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0093;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO“ZOO"
#data
FOO&#x0094;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO”ZOO"
#data
FOO&#x0095;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO•ZOO"
#data
FOO&#x0096;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x0097;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO—ZOO"
#data
FOO&#x0098;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO˜ZOO"
#data
FOO&#x0099;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO™ZOO"
#data
FOO&#x009A;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOšZOO"
#data
FOO&#x009B;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x009C;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOœZOO"
#data
FOO&#x009D;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x009E;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOžZOO"
#data
FOO&#x009F;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOŸZOO"
#data
FOO&#x00A0;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO ZOO"
#data
FOO&#xD7FF;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO퟿ZOO"
#data
FOO&#xD800;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#xD801;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#xDFFE;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#xDFFF;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#xE000;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOOZOO"
#data
FOO&#x10FFFE;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO􏿾ZOO"
#data
FOO&#x1087D4;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO􈟔ZOO"
#data
FOO&#x10FFFF;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO􏿿ZOO"
#data
FOO&#x110000;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"
#data
FOO&#xFFFFFF;ZOO
#errors
#document
| <html>
| <head>
| <body>
| "FOO<4F>ZOO"

View File

@ -0,0 +1,249 @@
#data
<div bar="ZZ&gt;YY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ>YY"
#data
<div bar="ZZ&"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&"
#data
<div bar='ZZ&'></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&"
#data
<div bar=ZZ&></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&"
#data
<div bar="ZZ&gt=YY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&gt=YY"
#data
<div bar="ZZ&gt0YY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&gt0YY"
#data
<div bar="ZZ&gt9YY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&gt9YY"
#data
<div bar="ZZ&gtaYY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&gtaYY"
#data
<div bar="ZZ&gtZYY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&gtZYY"
#data
<div bar="ZZ&gt YY"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ> YY"
#data
<div bar="ZZ&gt"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ>"
#data
<div bar='ZZ&gt'></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ>"
#data
<div bar=ZZ&gt></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ>"
#data
<div bar="ZZ&pound_id=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ£_id=23"
#data
<div bar="ZZ&prod_id=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&prod_id=23"
#data
<div bar="ZZ&pound;_id=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ£_id=23"
#data
<div bar="ZZ&prod;_id=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ∏_id=23"
#data
<div bar="ZZ&pound=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&pound=23"
#data
<div bar="ZZ&prod=23"></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| bar="ZZ&prod=23"
#data
<div>ZZ&pound_id=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ£_id=23"
#data
<div>ZZ&prod_id=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ&prod_id=23"
#data
<div>ZZ&pound;_id=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ£_id=23"
#data
<div>ZZ&prod;_id=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ∏_id=23"
#data
<div>ZZ&pound=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ£=23"
#data
<div>ZZ&prod=23</div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| "ZZ&prod=23"

View File

@ -0,0 +1,246 @@
#data
<div<div>
#errors
#document
| <html>
| <head>
| <body>
| <div<div>
#data
<div foo<bar=''>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| foo<bar=""
#data
<div foo=`bar`>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| foo="`bar`"
#data
<div \"foo=''>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| \"foo=""
#data
<a href='\nbar'></a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| href="\nbar"
#data
<!DOCTYPE html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
&lang;&rang;
#errors
#document
| <html>
| <head>
| <body>
| "⟨⟩"
#data
&apos;
#errors
#document
| <html>
| <head>
| <body>
| "'"
#data
&ImaginaryI;
#errors
#document
| <html>
| <head>
| <body>
| ""
#data
&Kopf;
#errors
#document
| <html>
| <head>
| <body>
| "𝕂"
#data
&notinva;
#errors
#document
| <html>
| <head>
| <body>
| "∉"
#data
<?import namespace="foo" implementation="#bar">
#errors
#document
| <!-- ?import namespace="foo" implementation="#bar" -->
| <html>
| <head>
| <body>
#data
<!--foo--bar-->
#errors
#document
| <!-- foo--bar -->
| <html>
| <head>
| <body>
#data
<![CDATA[x]]>
#errors
#document
| <!-- [CDATA[x]] -->
| <html>
| <head>
| <body>
#data
<textarea><!--</textarea>--></textarea>
#errors
#document
| <html>
| <head>
| <body>
| <textarea>
| "<!--"
| "-->"
#data
<textarea><!--</textarea>-->
#errors
#document
| <html>
| <head>
| <body>
| <textarea>
| "<!--"
| "-->"
#data
<style><!--</style>--></style>
#errors
#document
| <html>
| <head>
| <style>
| "<!--"
| <body>
| "-->"
#data
<style><!--</style>-->
#errors
#document
| <html>
| <head>
| <style>
| "<!--"
| <body>
| "-->"
#data
<ul><li>A </li> <li>B</li></ul>
#errors
#document
| <html>
| <head>
| <body>
| <ul>
| <li>
| "A "
| " "
| <li>
| "B"
#data
<table><form><input type=hidden><input></form><div></div></table>
#errors
#document
| <html>
| <head>
| <body>
| <input>
| <div>
| <table>
| <form>
| <input>
| type="hidden"
#data
<i>A<b>B<p></i>C</b>D
#errors
#document
| <html>
| <head>
| <body>
| <i>
| "A"
| <b>
| "B"
| <b>
| <p>
| <b>
| <i>
| "C"
| "D"
#data
<div></div>
#errors
#document
| <html>
| <head>
| <body>
| <div>
#data
<svg></svg>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
#data
<math></math>
#errors
#document
| <html>
| <head>
| <body>
| <math math>

View File

@ -0,0 +1,43 @@
#data
<button>1</foo>
#errors
#document
| <html>
| <head>
| <body>
| <button>
| "1"
#data
<foo>1<p>2</foo>
#errors
#document
| <html>
| <head>
| <body>
| <foo>
| "1"
| <p>
| "2"
#data
<dd>1</foo>
#errors
#document
| <html>
| <head>
| <body>
| <dd>
| "1"
#data
<foo>1<dd>2</foo>
#errors
#document
| <html>
| <head>
| <body>
| <foo>
| "1"
| <dd>
| "2"

View File

@ -0,0 +1,40 @@
#data
<isindex>
#errors
#document
| <html>
| <head>
| <body>
| <form>
| <hr>
| <label>
| "This is a searchable index. Enter search keywords: "
| <input>
| name="isindex"
| <hr>
#data
<isindex name="A" action="B" prompt="C" foo="D">
#errors
#document
| <html>
| <head>
| <body>
| <form>
| action="B"
| <hr>
| <label>
| "C"
| <input>
| foo="D"
| name="isindex"
| <hr>
#data
<form><isindex>
#errors
#document
| <html>
| <head>
| <body>
| <form>

View File

@ -0,0 +1,52 @@
#data
<input type="hidden"><frameset>
#errors
21: Start tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
31: “frameset” start tag seen.
31: End of file seen and there were open elements.
#document
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><table><caption><svg>foo</table>bar
#errors
47: End tag “table” did not match the name of the current open element (“svg”).
47: “table” closed but “caption” was still open.
47: End tag “table” seen, but there were open elements.
36: Unclosed element “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <svg svg>
| "foo"
| "bar"
#data
<table><tr><td><svg><desc><td></desc><circle>
#errors
7: Start tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
30: A table cell was implicitly closed, but there were open elements.
26: Unclosed element “desc”.
20: Unclosed element “svg”.
37: Stray end tag “desc”.
45: End of file seen and there were open elements.
45: Unclosed element “circle”.
7: Unclosed element “table”.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| <svg desc>
| <td>
| <circle>

Binary file not shown.

View File

@ -0,0 +1,308 @@
#data
FOO<script>'Hello'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'Hello'"
| "BAR"
#data
FOO<script></script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "BAR"
#data
FOO<script></script >BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "BAR"
#data
FOO<script></script/>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "BAR"
#data
FOO<script></script/ >BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "BAR"
#data
FOO<script type="text/plain"></scriptx>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "</scriptx>BAR"
#data
FOO<script></script foo=">" dd>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "BAR"
#data
FOO<script>'<'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<'"
| "BAR"
#data
FOO<script>'<!'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!'"
| "BAR"
#data
FOO<script>'<!-'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-'"
| "BAR"
#data
FOO<script>'<!--'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!--'"
| "BAR"
#data
FOO<script>'<!---'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!---'"
| "BAR"
#data
FOO<script>'<!-->'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-->'"
| "BAR"
#data
FOO<script>'<!-->'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-->'"
| "BAR"
#data
FOO<script>'<!-- potato'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-- potato'"
| "BAR"
#data
FOO<script>'<!-- <sCrIpt'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-- <sCrIpt'"
| "BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt>'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt>'</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt> -'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt> -'</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt> --'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt> --'</script>BAR"
#data
FOO<script>'<!-- <sCrIpt> -->'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| "'<!-- <sCrIpt> -->'"
| "BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt> --!>'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt> --!>'</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt> -- >'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt> -- >'</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt '</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt '</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt/'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt/'</script>BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt\'</script>BAR
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt\'"
| "BAR"
#data
FOO<script type="text/plain">'<!-- <sCrIpt/'</script>BAR</script>QUX
#errors
#document
| <html>
| <head>
| <body>
| "FOO"
| <script>
| type="text/plain"
| "'<!-- <sCrIpt/'</script>BAR"
| "QUX"

View File

@ -0,0 +1,15 @@
#data
<p><b id="A"><script>document.getElementById("A").id = "B"</script></p>TEXT</b>
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <b>
| id="B"
| <script>
| "document.getElementById("A").id = "B""
| <b>
| id="A"
| "TEXT"

View File

@ -0,0 +1,28 @@
#data
1<script>document.write("2")</script>3
#errors
#document
| <html>
| <head>
| <body>
| "1"
| <script>
| "document.write("2")"
| "23"
#data
1<script>document.write("<script>document.write('2')</scr"+ "ipt><script>document.write('3')</scr" + "ipt>")</script>4
#errors
#document
| <html>
| <head>
| <body>
| "1"
| <script>
| "document.write("<script>document.write('2')</scr"+ "ipt><script>document.write('3')</scr" + "ipt>")"
| <script>
| "document.write('2')"
| "2"
| <script>
| "document.write('3')"
| "34"

View File

@ -0,0 +1,212 @@
#data
<table><th>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <th>
#data
<table><td>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
#data
<table><col foo='bar'>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <colgroup>
| <col>
| foo="bar"
#data
<table><colgroup></html>foo
#errors
#document
| <html>
| <head>
| <body>
| "foo"
| <table>
| <colgroup>
#data
<table></table><p>foo
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <p>
| "foo"
#data
<table></body></caption></col></colgroup></html></tbody></td></tfoot></th></thead></tr><td>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
#data
<table><select><option>3</select></table>
#errors
#document
| <html>
| <head>
| <body>
| <select>
| <option>
| "3"
| <table>
#data
<table><select><table></table></select></table>
#errors
#document
| <html>
| <head>
| <body>
| <select>
| <table>
| <table>
#data
<table><select></table>
#errors
#document
| <html>
| <head>
| <body>
| <select>
| <table>
#data
<table><select><option>A<tr><td>B</td></tr></table>
#errors
#document
| <html>
| <head>
| <body>
| <select>
| <option>
| "A"
| <table>
| <tbody>
| <tr>
| <td>
| "B"
#data
<table><td></body></caption></col></colgroup></html>foo
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| "foo"
#data
<table><td>A</table>B
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| "A"
| "B"
#data
<table><tr><caption>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <caption>
#data
<table><tr></body></caption></col></colgroup></html></td></th><td>foo
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| "foo"
#data
<table><td><tr>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <tr>
#data
<table><td><button><td>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <button>
| <td>
#data
<table><tr><td><svg><desc><td>
#errors
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| <svg desc>
| <td>

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,799 @@
#data
<!DOCTYPE html><svg></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
#data
<!DOCTYPE html><svg></svg><![CDATA[a]]>
#errors
29: Bogus comment
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <!-- [CDATA[a]] -->
#data
<!DOCTYPE html><body><svg></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
#data
<!DOCTYPE html><body><select><svg></svg></select>
#errors
35: Stray “svg” start tag.
42: Stray end tag “svg”
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!DOCTYPE html><body><select><option><svg></svg></option></select>
#errors
43: Stray “svg” start tag.
50: Stray end tag “svg”
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <option>
#data
<!DOCTYPE html><body><table><svg></svg></table>
#errors
34: Start tag “svg” seen in “table”.
41: Stray end tag “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <table>
#data
<!DOCTYPE html><body><table><svg><g>foo</g></svg></table>
#errors
34: Start tag “svg” seen in “table”.
46: Stray end tag “g”.
53: Stray end tag “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <table>
#data
<!DOCTYPE html><body><table><svg><g>foo</g><g>bar</g></svg></table>
#errors
34: Start tag “svg” seen in “table”.
46: Stray end tag “g”.
58: Stray end tag “g”.
65: Stray end tag “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <table>
#data
<!DOCTYPE html><body><table><tbody><svg><g>foo</g><g>bar</g></svg></tbody></table>
#errors
41: Start tag “svg” seen in “table”.
53: Stray end tag “g”.
65: Stray end tag “g”.
72: Stray end tag “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <table>
| <tbody>
#data
<!DOCTYPE html><body><table><tbody><tr><svg><g>foo</g><g>bar</g></svg></tr></tbody></table>
#errors
45: Start tag “svg” seen in “table”.
57: Stray end tag “g”.
69: Stray end tag “g”.
76: Stray end tag “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <table>
| <tbody>
| <tr>
#data
<!DOCTYPE html><body><table><tbody><tr><td><svg><g>foo</g><g>bar</g></svg></td></tr></tbody></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
#data
<!DOCTYPE html><body><table><tbody><tr><td><svg><g>foo</g><g>bar</g></svg><p>baz</td></tr></tbody></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body><table><caption><svg><g>foo</g><g>bar</g></svg><p>baz</caption></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body><table><caption><svg><g>foo</g><g>bar</g><p>baz</table><p>quux
#errors
70: HTML start tag “p” in a foreign namespace context.
81: “table” closed but “caption” was still open.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><caption><svg><g>foo</g><g>bar</g>baz</table><p>quux
#errors
78: “table” closed but “caption” was still open.
78: Unclosed elements on stack.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| "baz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><colgroup><svg><g>foo</g><g>bar</g><p>baz</table><p>quux
#errors
44: Start tag “svg” seen in “table”.
56: Stray end tag “g”.
68: Stray end tag “g”.
71: HTML start tag “p” in a foreign namespace context.
71: Start tag “p” seen in “table”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
| <table>
| <colgroup>
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><tr><td><select><svg><g>foo</g><g>bar</g><p>baz</table><p>quux
#errors
50: Stray “svg” start tag.
54: Stray “g” start tag.
62: Stray end tag “g”
66: Stray “g” start tag.
74: Stray end tag “g”
77: Stray “p” start tag.
88: “table” end tag with “select” open.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <select>
| "foobarbaz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><select><svg><g>foo</g><g>bar</g><p>baz</table><p>quux
#errors
36: Start tag “select” seen in “table”.
42: Stray “svg” start tag.
46: Stray “g” start tag.
54: Stray end tag “g”
58: Stray “g” start tag.
66: Stray end tag “g”
69: Stray “p” start tag.
80: “table” end tag with “select” open.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| "foobarbaz"
| <table>
| <p>
| "quux"
#data
<!DOCTYPE html><body></body></html><svg><g>foo</g><g>bar</g><p>baz
#errors
41: Stray “svg” start tag.
68: HTML start tag “p” in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body></body><svg><g>foo</g><g>bar</g><p>baz
#errors
34: Stray “svg” start tag.
61: HTML start tag “p” in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg g>
| "foo"
| <svg g>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><frameset><svg><g></g><g></g><p><span>
#errors
31: Stray “svg” start tag.
35: Stray “g” start tag.
40: Stray end tag “g”
44: Stray “g” start tag.
49: Stray end tag “g”
52: Stray “p” start tag.
58: Stray “span” start tag.
58: End of file seen and there were open elements.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><frameset></frameset><svg><g></g><g></g><p><span>
#errors
42: Stray “svg” start tag.
46: Stray “g” start tag.
51: Stray end tag “g”
55: Stray “g” start tag.
60: Stray end tag “g”
63: Stray “p” start tag.
69: Stray “span” start tag.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><body xlink:href=foo><svg xlink:href=foo></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| <svg svg>
| xlink href="foo"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><svg><g xml:lang=en xlink:href=foo></g></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <svg svg>
| <svg g>
| xlink href="foo"
| xml lang="en"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><svg><g xml:lang=en xlink:href=foo /></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <svg svg>
| <svg g>
| xlink href="foo"
| xml lang="en"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><svg><g xml:lang=en xlink:href=foo />bar</svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <svg svg>
| <svg g>
| xlink href="foo"
| xml lang="en"
| "bar"
#data
<svg></path>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
#data
<div><svg></div>a
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| "a"
#data
<div><svg><path></div>a
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| <svg path>
| "a"
#data
<div><svg><path></svg><path>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| <svg path>
| <path>
#data
<div><svg><path><foreignObject><math></div>a
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| <svg path>
| <svg foreignObject>
| <math math>
| "a"
#data
<div><svg><path><foreignObject><p></div>a
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| <svg path>
| <svg foreignObject>
| <p>
| "a"
#data
<!DOCTYPE html><svg><desc><div><svg><ul>a
#errors
40: HTML start tag “ul” in a foreign namespace context.
41: End of file in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg desc>
| <div>
| <svg svg>
| <ul>
| "a"
#data
<!DOCTYPE html><svg><desc><svg><ul>a
#errors
35: HTML start tag “ul” in a foreign namespace context.
36: End of file in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg desc>
| <svg svg>
| <ul>
| "a"
#data
<!DOCTYPE html><p><svg><desc><p>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <svg svg>
| <svg desc>
| <p>
#data
<!DOCTYPE html><p><svg><title><p>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <svg svg>
| <svg title>
| <p>
#data
<div><svg><path><foreignObject><p></foreignObject><p>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <svg svg>
| <svg path>
| <svg foreignObject>
| <p>
| <p>
#data
<math><mi><div><object><div><span></span></div></object></div></mi><mi>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| <div>
| <object>
| <div>
| <span>
| <math mi>
#data
<math><mi><svg><foreignObject><div><div></div></div></foreignObject></svg></mi><mi>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| <svg svg>
| <svg foreignObject>
| <div>
| <div>
| <math mi>
#data
<svg><script></script><path>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| <svg script>
| <svg path>
#data
<table><svg></svg><tr>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| <table>
| <tbody>
| <tr>
#data
<math><mi><mglyph>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| <math mglyph>
#data
<math><mi><malignmark>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| <math malignmark>
#data
<math><mo><mglyph>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mo>
| <math mglyph>
#data
<math><mo><malignmark>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mo>
| <math malignmark>
#data
<math><mn><mglyph>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mn>
| <math mglyph>
#data
<math><mn><malignmark>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mn>
| <math malignmark>
#data
<math><ms><mglyph>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math ms>
| <math mglyph>
#data
<math><ms><malignmark>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math ms>
| <math malignmark>
#data
<math><mtext><mglyph>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mtext>
| <math mglyph>
#data
<math><mtext><malignmark>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math mtext>
| <math malignmark>
#data
<math><annotation-xml><svg></svg></annotation-xml><mi>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| <svg svg>
| <math mi>
#data
<math><annotation-xml><svg><foreignObject><div><math><mi></mi></math><span></span></div></foreignObject><path></path></svg></annotation-xml><mi>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| <svg svg>
| <svg foreignObject>
| <div>
| <math math>
| <math mi>
| <span>
| <svg path>
| <math mi>
#data
<math><annotation-xml><svg><foreignObject><math><mi><svg></svg></mi><mo></mo></math><span></span></foreignObject><path></path></svg></annotation-xml><mi>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| <svg svg>
| <svg foreignObject>
| <math math>
| <math mi>
| <svg svg>
| <math mo>
| <span>
| <svg path>
| <math mi>

View File

@ -0,0 +1,482 @@
#data
<!DOCTYPE html><body><svg attributeName='' attributeType='' baseFrequency='' baseProfile='' calcMode='' clipPathUnits='' contentScriptType='' contentStyleType='' diffuseConstant='' edgeMode='' externalResourcesRequired='' filterRes='' filterUnits='' glyphRef='' gradientTransform='' gradientUnits='' kernelMatrix='' kernelUnitLength='' keyPoints='' keySplines='' keyTimes='' lengthAdjust='' limitingConeAngle='' markerHeight='' markerUnits='' markerWidth='' maskContentUnits='' maskUnits='' numOctaves='' pathLength='' patternContentUnits='' patternTransform='' patternUnits='' pointsAtX='' pointsAtY='' pointsAtZ='' preserveAlpha='' preserveAspectRatio='' primitiveUnits='' refX='' refY='' repeatCount='' repeatDur='' requiredExtensions='' requiredFeatures='' specularConstant='' specularExponent='' spreadMethod='' startOffset='' stdDeviation='' stitchTiles='' surfaceScale='' systemLanguage='' tableValues='' targetX='' targetY='' textLength='' viewBox='' viewTarget='' xChannelSelector='' yChannelSelector='' zoomAndPan=''></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| attributeName=""
| attributeType=""
| baseFrequency=""
| baseProfile=""
| calcMode=""
| clipPathUnits=""
| contentScriptType=""
| contentStyleType=""
| diffuseConstant=""
| edgeMode=""
| externalResourcesRequired=""
| filterRes=""
| filterUnits=""
| glyphRef=""
| gradientTransform=""
| gradientUnits=""
| kernelMatrix=""
| kernelUnitLength=""
| keyPoints=""
| keySplines=""
| keyTimes=""
| lengthAdjust=""
| limitingConeAngle=""
| markerHeight=""
| markerUnits=""
| markerWidth=""
| maskContentUnits=""
| maskUnits=""
| numOctaves=""
| pathLength=""
| patternContentUnits=""
| patternTransform=""
| patternUnits=""
| pointsAtX=""
| pointsAtY=""
| pointsAtZ=""
| preserveAlpha=""
| preserveAspectRatio=""
| primitiveUnits=""
| refX=""
| refY=""
| repeatCount=""
| repeatDur=""
| requiredExtensions=""
| requiredFeatures=""
| specularConstant=""
| specularExponent=""
| spreadMethod=""
| startOffset=""
| stdDeviation=""
| stitchTiles=""
| surfaceScale=""
| systemLanguage=""
| tableValues=""
| targetX=""
| targetY=""
| textLength=""
| viewBox=""
| viewTarget=""
| xChannelSelector=""
| yChannelSelector=""
| zoomAndPan=""
#data
<!DOCTYPE html><BODY><SVG ATTRIBUTENAME='' ATTRIBUTETYPE='' BASEFREQUENCY='' BASEPROFILE='' CALCMODE='' CLIPPATHUNITS='' CONTENTSCRIPTTYPE='' CONTENTSTYLETYPE='' DIFFUSECONSTANT='' EDGEMODE='' EXTERNALRESOURCESREQUIRED='' FILTERRES='' FILTERUNITS='' GLYPHREF='' GRADIENTTRANSFORM='' GRADIENTUNITS='' KERNELMATRIX='' KERNELUNITLENGTH='' KEYPOINTS='' KEYSPLINES='' KEYTIMES='' LENGTHADJUST='' LIMITINGCONEANGLE='' MARKERHEIGHT='' MARKERUNITS='' MARKERWIDTH='' MASKCONTENTUNITS='' MASKUNITS='' NUMOCTAVES='' PATHLENGTH='' PATTERNCONTENTUNITS='' PATTERNTRANSFORM='' PATTERNUNITS='' POINTSATX='' POINTSATY='' POINTSATZ='' PRESERVEALPHA='' PRESERVEASPECTRATIO='' PRIMITIVEUNITS='' REFX='' REFY='' REPEATCOUNT='' REPEATDUR='' REQUIREDEXTENSIONS='' REQUIREDFEATURES='' SPECULARCONSTANT='' SPECULAREXPONENT='' SPREADMETHOD='' STARTOFFSET='' STDDEVIATION='' STITCHTILES='' SURFACESCALE='' SYSTEMLANGUAGE='' TABLEVALUES='' TARGETX='' TARGETY='' TEXTLENGTH='' VIEWBOX='' VIEWTARGET='' XCHANNELSELECTOR='' YCHANNELSELECTOR='' ZOOMANDPAN=''></SVG>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| attributeName=""
| attributeType=""
| baseFrequency=""
| baseProfile=""
| calcMode=""
| clipPathUnits=""
| contentScriptType=""
| contentStyleType=""
| diffuseConstant=""
| edgeMode=""
| externalResourcesRequired=""
| filterRes=""
| filterUnits=""
| glyphRef=""
| gradientTransform=""
| gradientUnits=""
| kernelMatrix=""
| kernelUnitLength=""
| keyPoints=""
| keySplines=""
| keyTimes=""
| lengthAdjust=""
| limitingConeAngle=""
| markerHeight=""
| markerUnits=""
| markerWidth=""
| maskContentUnits=""
| maskUnits=""
| numOctaves=""
| pathLength=""
| patternContentUnits=""
| patternTransform=""
| patternUnits=""
| pointsAtX=""
| pointsAtY=""
| pointsAtZ=""
| preserveAlpha=""
| preserveAspectRatio=""
| primitiveUnits=""
| refX=""
| refY=""
| repeatCount=""
| repeatDur=""
| requiredExtensions=""
| requiredFeatures=""
| specularConstant=""
| specularExponent=""
| spreadMethod=""
| startOffset=""
| stdDeviation=""
| stitchTiles=""
| surfaceScale=""
| systemLanguage=""
| tableValues=""
| targetX=""
| targetY=""
| textLength=""
| viewBox=""
| viewTarget=""
| xChannelSelector=""
| yChannelSelector=""
| zoomAndPan=""
#data
<!DOCTYPE html><body><svg attributename='' attributetype='' basefrequency='' baseprofile='' calcmode='' clippathunits='' contentscripttype='' contentstyletype='' diffuseconstant='' edgemode='' externalresourcesrequired='' filterres='' filterunits='' glyphref='' gradienttransform='' gradientunits='' kernelmatrix='' kernelunitlength='' keypoints='' keysplines='' keytimes='' lengthadjust='' limitingconeangle='' markerheight='' markerunits='' markerwidth='' maskcontentunits='' maskunits='' numoctaves='' pathlength='' patterncontentunits='' patterntransform='' patternunits='' pointsatx='' pointsaty='' pointsatz='' preservealpha='' preserveaspectratio='' primitiveunits='' refx='' refy='' repeatcount='' repeatdur='' requiredextensions='' requiredfeatures='' specularconstant='' specularexponent='' spreadmethod='' startoffset='' stddeviation='' stitchtiles='' surfacescale='' systemlanguage='' tablevalues='' targetx='' targety='' textlength='' viewbox='' viewtarget='' xchannelselector='' ychannelselector='' zoomandpan=''></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| attributeName=""
| attributeType=""
| baseFrequency=""
| baseProfile=""
| calcMode=""
| clipPathUnits=""
| contentScriptType=""
| contentStyleType=""
| diffuseConstant=""
| edgeMode=""
| externalResourcesRequired=""
| filterRes=""
| filterUnits=""
| glyphRef=""
| gradientTransform=""
| gradientUnits=""
| kernelMatrix=""
| kernelUnitLength=""
| keyPoints=""
| keySplines=""
| keyTimes=""
| lengthAdjust=""
| limitingConeAngle=""
| markerHeight=""
| markerUnits=""
| markerWidth=""
| maskContentUnits=""
| maskUnits=""
| numOctaves=""
| pathLength=""
| patternContentUnits=""
| patternTransform=""
| patternUnits=""
| pointsAtX=""
| pointsAtY=""
| pointsAtZ=""
| preserveAlpha=""
| preserveAspectRatio=""
| primitiveUnits=""
| refX=""
| refY=""
| repeatCount=""
| repeatDur=""
| requiredExtensions=""
| requiredFeatures=""
| specularConstant=""
| specularExponent=""
| spreadMethod=""
| startOffset=""
| stdDeviation=""
| stitchTiles=""
| surfaceScale=""
| systemLanguage=""
| tableValues=""
| targetX=""
| targetY=""
| textLength=""
| viewBox=""
| viewTarget=""
| xChannelSelector=""
| yChannelSelector=""
| zoomAndPan=""
#data
<!DOCTYPE html><body><math attributeName='' attributeType='' baseFrequency='' baseProfile='' calcMode='' clipPathUnits='' contentScriptType='' contentStyleType='' diffuseConstant='' edgeMode='' externalResourcesRequired='' filterRes='' filterUnits='' glyphRef='' gradientTransform='' gradientUnits='' kernelMatrix='' kernelUnitLength='' keyPoints='' keySplines='' keyTimes='' lengthAdjust='' limitingConeAngle='' markerHeight='' markerUnits='' markerWidth='' maskContentUnits='' maskUnits='' numOctaves='' pathLength='' patternContentUnits='' patternTransform='' patternUnits='' pointsAtX='' pointsAtY='' pointsAtZ='' preserveAlpha='' preserveAspectRatio='' primitiveUnits='' refX='' refY='' repeatCount='' repeatDur='' requiredExtensions='' requiredFeatures='' specularConstant='' specularExponent='' spreadMethod='' startOffset='' stdDeviation='' stitchTiles='' surfaceScale='' systemLanguage='' tableValues='' targetX='' targetY='' textLength='' viewBox='' viewTarget='' xChannelSelector='' yChannelSelector='' zoomAndPan=''></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| attributename=""
| attributetype=""
| basefrequency=""
| baseprofile=""
| calcmode=""
| clippathunits=""
| contentscripttype=""
| contentstyletype=""
| diffuseconstant=""
| edgemode=""
| externalresourcesrequired=""
| filterres=""
| filterunits=""
| glyphref=""
| gradienttransform=""
| gradientunits=""
| kernelmatrix=""
| kernelunitlength=""
| keypoints=""
| keysplines=""
| keytimes=""
| lengthadjust=""
| limitingconeangle=""
| markerheight=""
| markerunits=""
| markerwidth=""
| maskcontentunits=""
| maskunits=""
| numoctaves=""
| pathlength=""
| patterncontentunits=""
| patterntransform=""
| patternunits=""
| pointsatx=""
| pointsaty=""
| pointsatz=""
| preservealpha=""
| preserveaspectratio=""
| primitiveunits=""
| refx=""
| refy=""
| repeatcount=""
| repeatdur=""
| requiredextensions=""
| requiredfeatures=""
| specularconstant=""
| specularexponent=""
| spreadmethod=""
| startoffset=""
| stddeviation=""
| stitchtiles=""
| surfacescale=""
| systemlanguage=""
| tablevalues=""
| targetx=""
| targety=""
| textlength=""
| viewbox=""
| viewtarget=""
| xchannelselector=""
| ychannelselector=""
| zoomandpan=""
#data
<!DOCTYPE html><body><svg><altGlyph /><altGlyphDef /><altGlyphItem /><animateColor /><animateMotion /><animateTransform /><clipPath /><feBlend /><feColorMatrix /><feComponentTransfer /><feComposite /><feConvolveMatrix /><feDiffuseLighting /><feDisplacementMap /><feDistantLight /><feFlood /><feFuncA /><feFuncB /><feFuncG /><feFuncR /><feGaussianBlur /><feImage /><feMerge /><feMergeNode /><feMorphology /><feOffset /><fePointLight /><feSpecularLighting /><feSpotLight /><feTile /><feTurbulence /><foreignObject /><glyphRef /><linearGradient /><radialGradient /><textPath /></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg altGlyph>
| <svg altGlyphDef>
| <svg altGlyphItem>
| <svg animateColor>
| <svg animateMotion>
| <svg animateTransform>
| <svg clipPath>
| <svg feBlend>
| <svg feColorMatrix>
| <svg feComponentTransfer>
| <svg feComposite>
| <svg feConvolveMatrix>
| <svg feDiffuseLighting>
| <svg feDisplacementMap>
| <svg feDistantLight>
| <svg feFlood>
| <svg feFuncA>
| <svg feFuncB>
| <svg feFuncG>
| <svg feFuncR>
| <svg feGaussianBlur>
| <svg feImage>
| <svg feMerge>
| <svg feMergeNode>
| <svg feMorphology>
| <svg feOffset>
| <svg fePointLight>
| <svg feSpecularLighting>
| <svg feSpotLight>
| <svg feTile>
| <svg feTurbulence>
| <svg foreignObject>
| <svg glyphRef>
| <svg linearGradient>
| <svg radialGradient>
| <svg textPath>
#data
<!DOCTYPE html><body><svg><altglyph /><altglyphdef /><altglyphitem /><animatecolor /><animatemotion /><animatetransform /><clippath /><feblend /><fecolormatrix /><fecomponenttransfer /><fecomposite /><feconvolvematrix /><fediffuselighting /><fedisplacementmap /><fedistantlight /><feflood /><fefunca /><fefuncb /><fefuncg /><fefuncr /><fegaussianblur /><feimage /><femerge /><femergenode /><femorphology /><feoffset /><fepointlight /><fespecularlighting /><fespotlight /><fetile /><feturbulence /><foreignobject /><glyphref /><lineargradient /><radialgradient /><textpath /></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg altGlyph>
| <svg altGlyphDef>
| <svg altGlyphItem>
| <svg animateColor>
| <svg animateMotion>
| <svg animateTransform>
| <svg clipPath>
| <svg feBlend>
| <svg feColorMatrix>
| <svg feComponentTransfer>
| <svg feComposite>
| <svg feConvolveMatrix>
| <svg feDiffuseLighting>
| <svg feDisplacementMap>
| <svg feDistantLight>
| <svg feFlood>
| <svg feFuncA>
| <svg feFuncB>
| <svg feFuncG>
| <svg feFuncR>
| <svg feGaussianBlur>
| <svg feImage>
| <svg feMerge>
| <svg feMergeNode>
| <svg feMorphology>
| <svg feOffset>
| <svg fePointLight>
| <svg feSpecularLighting>
| <svg feSpotLight>
| <svg feTile>
| <svg feTurbulence>
| <svg foreignObject>
| <svg glyphRef>
| <svg linearGradient>
| <svg radialGradient>
| <svg textPath>
#data
<!DOCTYPE html><BODY><SVG><ALTGLYPH /><ALTGLYPHDEF /><ALTGLYPHITEM /><ANIMATECOLOR /><ANIMATEMOTION /><ANIMATETRANSFORM /><CLIPPATH /><FEBLEND /><FECOLORMATRIX /><FECOMPONENTTRANSFER /><FECOMPOSITE /><FECONVOLVEMATRIX /><FEDIFFUSELIGHTING /><FEDISPLACEMENTMAP /><FEDISTANTLIGHT /><FEFLOOD /><FEFUNCA /><FEFUNCB /><FEFUNCG /><FEFUNCR /><FEGAUSSIANBLUR /><FEIMAGE /><FEMERGE /><FEMERGENODE /><FEMORPHOLOGY /><FEOFFSET /><FEPOINTLIGHT /><FESPECULARLIGHTING /><FESPOTLIGHT /><FETILE /><FETURBULENCE /><FOREIGNOBJECT /><GLYPHREF /><LINEARGRADIENT /><RADIALGRADIENT /><TEXTPATH /></SVG>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg altGlyph>
| <svg altGlyphDef>
| <svg altGlyphItem>
| <svg animateColor>
| <svg animateMotion>
| <svg animateTransform>
| <svg clipPath>
| <svg feBlend>
| <svg feColorMatrix>
| <svg feComponentTransfer>
| <svg feComposite>
| <svg feConvolveMatrix>
| <svg feDiffuseLighting>
| <svg feDisplacementMap>
| <svg feDistantLight>
| <svg feFlood>
| <svg feFuncA>
| <svg feFuncB>
| <svg feFuncG>
| <svg feFuncR>
| <svg feGaussianBlur>
| <svg feImage>
| <svg feMerge>
| <svg feMergeNode>
| <svg feMorphology>
| <svg feOffset>
| <svg fePointLight>
| <svg feSpecularLighting>
| <svg feSpotLight>
| <svg feTile>
| <svg feTurbulence>
| <svg foreignObject>
| <svg glyphRef>
| <svg linearGradient>
| <svg radialGradient>
| <svg textPath>
#data
<!DOCTYPE html><body><math><altGlyph /><altGlyphDef /><altGlyphItem /><animateColor /><animateMotion /><animateTransform /><clipPath /><feBlend /><feColorMatrix /><feComponentTransfer /><feComposite /><feConvolveMatrix /><feDiffuseLighting /><feDisplacementMap /><feDistantLight /><feFlood /><feFuncA /><feFuncB /><feFuncG /><feFuncR /><feGaussianBlur /><feImage /><feMerge /><feMergeNode /><feMorphology /><feOffset /><fePointLight /><feSpecularLighting /><feSpotLight /><feTile /><feTurbulence /><foreignObject /><glyphRef /><linearGradient /><radialGradient /><textPath /></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math altglyph>
| <math altglyphdef>
| <math altglyphitem>
| <math animatecolor>
| <math animatemotion>
| <math animatetransform>
| <math clippath>
| <math feblend>
| <math fecolormatrix>
| <math fecomponenttransfer>
| <math fecomposite>
| <math feconvolvematrix>
| <math fediffuselighting>
| <math fedisplacementmap>
| <math fedistantlight>
| <math feflood>
| <math fefunca>
| <math fefuncb>
| <math fefuncg>
| <math fefuncr>
| <math fegaussianblur>
| <math feimage>
| <math femerge>
| <math femergenode>
| <math femorphology>
| <math feoffset>
| <math fepointlight>
| <math fespecularlighting>
| <math fespotlight>
| <math fetile>
| <math feturbulence>
| <math foreignobject>
| <math glyphref>
| <math lineargradient>
| <math radialgradient>
| <math textpath>
#data
<!DOCTYPE html><body><svg><solidColor /></svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg solidcolor>

View File

@ -0,0 +1,62 @@
#data
<!DOCTYPE html><body><p>foo<math><mtext><i>baz</i></mtext><annotation-xml><svg><desc><b>eggs</b></desc><g><foreignObject><P>spam<TABLE><tr><td><img></td></table></foreignObject></g><g>quux</g></svg></annotation-xml></math>bar
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| "foo"
| <math math>
| <math mtext>
| <i>
| "baz"
| <math annotation-xml>
| <svg svg>
| <svg desc>
| <b>
| "eggs"
| <svg g>
| <svg foreignObject>
| <p>
| "spam"
| <table>
| <tbody>
| <tr>
| <td>
| <img>
| <svg g>
| "quux"
| "bar"
#data
<!DOCTYPE html><body>foo<math><mtext><i>baz</i></mtext><annotation-xml><svg><desc><b>eggs</b></desc><g><foreignObject><P>spam<TABLE><tr><td><img></td></table></foreignObject></g><g>quux</g></svg></annotation-xml></math>bar
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "foo"
| <math math>
| <math mtext>
| <i>
| "baz"
| <math annotation-xml>
| <svg svg>
| <svg desc>
| <b>
| "eggs"
| <svg g>
| <svg foreignObject>
| <p>
| "spam"
| <table>
| <tbody>
| <tr>
| <td>
| <img>
| <svg g>
| "quux"
| "bar"

View File

@ -0,0 +1,74 @@
#data
<!DOCTYPE html><html><body><xyz:abc></xyz:abc>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <xyz:abc>
#data
<!DOCTYPE html><html><body><xyz:abc></xyz:abc><span></span>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <xyz:abc>
| <span>
#data
<!DOCTYPE html><html><html abc:def=gh><xyz:abc></xyz:abc>
#errors
15: Unexpected start tag html
#document
| <!DOCTYPE html>
| <html>
| abc:def="gh"
| <head>
| <body>
| <xyz:abc>
#data
<!DOCTYPE html><html xml:lang=bar><html xml:lang=foo>
#errors
15: Unexpected start tag html
#document
| <!DOCTYPE html>
| <html>
| xml:lang="bar"
| <head>
| <body>
#data
<!DOCTYPE html><html 123=456>
#errors
#document
| <!DOCTYPE html>
| <html>
| 123="456"
| <head>
| <body>
#data
<!DOCTYPE html><html 123=456><html 789=012>
#errors
#document
| <!DOCTYPE html>
| <html>
| 123="456"
| 789="012"
| <head>
| <body>
#data
<!DOCTYPE html><html><body 789=012>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| 789="012"

View File

@ -0,0 +1,208 @@
#data
<!DOCTYPE html><p><b><i><u></p> <p>X
#errors
Line: 1 Col: 31 Unexpected end tag (p). Ignored.
Line: 1 Col: 36 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <b>
| <i>
| <u>
| <b>
| <i>
| <u>
| " "
| <p>
| "X"
#data
<p><b><i><u></p>
<p>X
#errors
Line: 1 Col: 3 Unexpected start tag (p). Expected DOCTYPE.
Line: 1 Col: 16 Unexpected end tag (p). Ignored.
Line: 2 Col: 4 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <p>
| <b>
| <i>
| <u>
| <b>
| <i>
| <u>
| "
"
| <p>
| "X"
#data
<!doctype html></html> <head>
#errors
Line: 1 Col: 22 Unexpected end tag (html) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| " "
#data
<!doctype html></body><meta>
#errors
Line: 1 Col: 22 Unexpected end tag (body) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <meta>
#data
<html></html><!-- foo -->
#errors
Line: 1 Col: 6 Unexpected start tag (html). Expected DOCTYPE.
Line: 1 Col: 13 Unexpected end tag (html) after the (implied) root element.
#document
| <html>
| <head>
| <body>
| <!-- foo -->
#data
<!doctype html></body><title>X</title>
#errors
Line: 1 Col: 22 Unexpected end tag (body) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <title>
| "X"
#data
<!doctype html><table> X<meta></table>
#errors
Line: 1 Col: 24 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 30 Unexpected start tag (meta) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| " X"
| <meta>
| <table>
#data
<!doctype html><table> x</table>
#errors
Line: 1 Col: 24 Unexpected non-space characters in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| " x"
| <table>
#data
<!doctype html><table> x </table>
#errors
Line: 1 Col: 25 Unexpected non-space characters in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| " x "
| <table>
#data
<!doctype html><table><tr> x</table>
#errors
Line: 1 Col: 28 Unexpected non-space characters in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| " x"
| <table>
| <tbody>
| <tr>
#data
<!doctype html><table>X<style> <tr>x </style> </table>
#errors
Line: 1 Col: 23 Unexpected non-space characters in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
| <table>
| <style>
| " <tr>x "
| " "
#data
<!doctype html><div><table><a>foo</a> <tr><td>bar</td> </tr></table></div>
#errors
Line: 1 Col: 30 Unexpected start tag (a) in table context caused voodoo mode.
Line: 1 Col: 37 Unexpected end tag (a) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <div>
| <a>
| "foo"
| <table>
| " "
| <tbody>
| <tr>
| <td>
| "bar"
| " "
#data
<frame></frame></frame><frameset><frame><frameset><frame></frameset><noframes></frameset><noframes>
#errors
6: Start tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
13: Stray start tag “frame”.
21: Stray end tag “frame”.
29: Stray end tag “frame”.
39: “frameset” start tag after “body” already open.
105: End of file seen inside an [R]CDATA element.
105: End of file seen and there were open elements.
XXX: These errors are wrong, please fix me!
#document
| <html>
| <head>
| <frameset>
| <frame>
| <frameset>
| <frame>
| <noframes>
| "</frameset><noframes>"
#data
<!DOCTYPE html><object></html>
#errors
1: Expected closing tag. Unexpected end of file
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <object>

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,153 @@
#data
<!doctype html><table><tbody><select><tr>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <table>
| <tbody>
| <tr>
#data
<!doctype html><table><tr><select><td>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <table>
| <tbody>
| <tr>
| <td>
#data
<!doctype html><table><tr><td><select><td>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <select>
| <td>
#data
<!doctype html><table><tr><th><select><td>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <th>
| <select>
| <td>
#data
<!doctype html><table><caption><select><tr>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <select>
| <tbody>
| <tr>
#data
<!doctype html><select><tr>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><td>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><th>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><tbody>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><thead>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><tfoot>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><select><caption>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!doctype html><table><tr></table>a
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| "a"

View File

@ -0,0 +1,269 @@
#data
<!doctype html><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
#data
<!doctype html><table><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
| <table>
#data
<!doctype html><table><tbody><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
| <table>
| <tbody>
#data
<!doctype html><table><tbody><tr><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
| <table>
| <tbody>
| <tr>
#data
<!doctype html><table><tbody><tr><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
| <table>
| <tbody>
| <tr>
#data
<!doctype html><table><td><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <plaintext>
| "</plaintext>"
#data
<!doctype html><table><caption><plaintext></plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <plaintext>
| "</plaintext>"
#data
<!doctype html><table><tr><style></script></style>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "abc"
| <table>
| <tbody>
| <tr>
| <style>
| "</script>"
#data
<!doctype html><table><tr><script></style></script>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "abc"
| <table>
| <tbody>
| <tr>
| <script>
| "</style>"
#data
<!doctype html><table><caption><style></script></style>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <style>
| "</script>"
| "abc"
#data
<!doctype html><table><td><style></script></style>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <style>
| "</script>"
| "abc"
#data
<!doctype html><select><script></style></script>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <script>
| "</style>"
| "abc"
#data
<!doctype html><table><select><script></style></script>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <script>
| "</style>"
| "abc"
| <table>
#data
<!doctype html><table><tr><select><script></style></script>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <script>
| "</style>"
| "abc"
| <table>
| <tbody>
| <tr>
#data
<!doctype html><frameset></frameset><noframes>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
| <noframes>
| "abc"
#data
<!doctype html><frameset></frameset><noframes>abc</noframes><!--abc-->
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
| <noframes>
| "abc"
| <!-- abc -->
#data
<!doctype html><frameset></frameset></html><noframes>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
| <noframes>
| "abc"
#data
<!doctype html><frameset></frameset></html><noframes>abc</noframes><!--abc-->
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
| <noframes>
| "abc"
| <!-- abc -->
#data
<!doctype html><table><tr></tbody><tfoot>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <tfoot>
#data
<!doctype html><table><td><svg></svg>abc<td>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| "abc"
| <td>

File diff suppressed because it is too large Load Diff

View File

@ -0,0 +1,763 @@
#data
<!DOCTYPE html>Test
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "Test"
#data
<textarea>test</div>test
#errors
Line: 1 Col: 10 Unexpected start tag (textarea). Expected DOCTYPE.
Line: 1 Col: 24 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <textarea>
| "test</div>test"
#data
<table><td>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 11 Unexpected table cell start tag (td) in the table body phase.
Line: 1 Col: 11 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
#data
<table><td>test</tbody></table>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 11 Unexpected table cell start tag (td) in the table body phase.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| "test"
#data
<frame>test
#errors
Line: 1 Col: 7 Unexpected start tag (frame). Expected DOCTYPE.
Line: 1 Col: 7 Unexpected start tag frame. Ignored.
#document
| <html>
| <head>
| <body>
| "test"
#data
<!DOCTYPE html><frameset>test
#errors
Line: 1 Col: 29 Unepxected characters in the frameset phase. Characters ignored.
Line: 1 Col: 29 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><frameset><!DOCTYPE html>
#errors
Line: 1 Col: 40 Unexpected DOCTYPE. Ignored.
Line: 1 Col: 40 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><font><p><b>test</font>
#errors
Line: 1 Col: 38 End tag (font) violates step 1, paragraph 3 of the adoption agency algorithm.
Line: 1 Col: 38 End tag (font) violates step 1, paragraph 3 of the adoption agency algorithm.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <font>
| <p>
| <font>
| <b>
| "test"
#data
<!DOCTYPE html><dt><div><dd>
#errors
Line: 1 Col: 28 Missing end tag (div, dt).
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <dt>
| <div>
| <dd>
#data
<script></x
#errors
Line: 1 Col: 8 Unexpected start tag (script). Expected DOCTYPE.
Line: 1 Col: 11 Unexpected end of file. Expected end tag (script).
#document
| <html>
| <head>
| <script>
| "</x"
| <body>
#data
<table><plaintext><td>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 18 Unexpected start tag (plaintext) in table context caused voodoo mode.
Line: 1 Col: 22 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <plaintext>
| "<td>"
| <table>
#data
<plaintext></plaintext>
#errors
Line: 1 Col: 11 Unexpected start tag (plaintext). Expected DOCTYPE.
Line: 1 Col: 23 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <plaintext>
| "</plaintext>"
#data
<!DOCTYPE html><table><tr>TEST
#errors
Line: 1 Col: 30 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 30 Unexpected end of file. Expected table content.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "TEST"
| <table>
| <tbody>
| <tr>
#data
<!DOCTYPE html><body t1=1><body t2=2><body t3=3 t4=4>
#errors
Line: 1 Col: 37 Unexpected start tag (body).
Line: 1 Col: 53 Unexpected start tag (body).
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| t1="1"
| t2="2"
| t3="3"
| t4="4"
#data
</b test
#errors
Line: 1 Col: 8 Unexpected end of file in attribute name.
Line: 1 Col: 8 End tag contains unexpected attributes.
Line: 1 Col: 8 Unexpected end tag (b). Expected DOCTYPE.
Line: 1 Col: 8 Unexpected end tag (b) after the (implied) root element.
#document
| <html>
| <head>
| <body>
#data
<!DOCTYPE html></b test<b &=&amp>X
#errors
Line: 1 Col: 32 Named entity didn't end with ';'.
Line: 1 Col: 33 End tag contains unexpected attributes.
Line: 1 Col: 33 Unexpected end tag (b) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
#data
<!doctypehtml><scrIPt type=text/x-foobar;baz>X</SCRipt
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
Line: 1 Col: 54 Unexpected end of file in the tag name.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <script>
| type="text/x-foobar;baz"
| "X</SCRipt"
| <body>
#data
&
#errors
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&"
#data
&#
#errors
Line: 1 Col: 1 Numeric entity expected. Got end of file instead.
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&#"
#data
&#X
#errors
Line: 1 Col: 3 Numeric entity expected but none found.
Line: 1 Col: 3 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&#X"
#data
&#x
#errors
Line: 1 Col: 3 Numeric entity expected but none found.
Line: 1 Col: 3 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&#x"
#data
&#45
#errors
Line: 1 Col: 4 Numeric entity didn't end with ';'.
Line: 1 Col: 4 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "-"
#data
&x-test
#errors
Line: 1 Col: 1 Named entity expected. Got none.
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&x-test"
#data
<!doctypehtml><p><li>
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <li>
#data
<!doctypehtml><p><dt>
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <dt>
#data
<!doctypehtml><p><dd>
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <dd>
#data
<!doctypehtml><p><form>
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
Line: 1 Col: 23 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <form>
#data
<!DOCTYPE html><p></P>X
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| "X"
#data
&AMP
#errors
Line: 1 Col: 4 Named entity didn't end with ';'.
Line: 1 Col: 4 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&"
#data
&AMp;
#errors
Line: 1 Col: 1 Named entity expected. Got none.
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "&AMp;"
#data
<!DOCTYPE html><html><head></head><body><thisISasillyTESTelementNameToMakeSureCrazyTagNamesArePARSEDcorrectLY>
#errors
Line: 1 Col: 110 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <thisisasillytestelementnametomakesurecrazytagnamesareparsedcorrectly>
#data
<!DOCTYPE html>X</body>X
#errors
Line: 1 Col: 24 Unexpected non-space characters in the after body phase.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "XX"
#data
<!DOCTYPE html><!-- X
#errors
Line: 1 Col: 21 Unexpected end of file in comment.
#document
| <!DOCTYPE html>
| <!-- X -->
| <html>
| <head>
| <body>
#data
<!DOCTYPE html><table><caption>test TEST</caption><td>test
#errors
Line: 1 Col: 54 Unexpected table cell start tag (td) in the table body phase.
Line: 1 Col: 58 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| "test TEST"
| <tbody>
| <tr>
| <td>
| "test"
#data
<!DOCTYPE html><select><option><optgroup>
#errors
Line: 1 Col: 41 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <option>
| <optgroup>
#data
<!DOCTYPE html><select><optgroup><option></optgroup><option><select><option>
#errors
Line: 1 Col: 68 Unexpected select start tag in the select phase treated as select end tag.
Line: 1 Col: 76 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <optgroup>
| <option>
| <option>
| <option>
#data
<!DOCTYPE html><select><optgroup><option><optgroup>
#errors
Line: 1 Col: 51 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <optgroup>
| <option>
| <optgroup>
#data
<!DOCTYPE html><datalist><option>foo</datalist>bar
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <datalist>
| <option>
| "foo"
| "bar"
#data
<!DOCTYPE html><font><input><input></font>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <font>
| <input>
| <input>
#data
<!DOCTYPE html><!-- XXX - XXX -->
#errors
#document
| <!DOCTYPE html>
| <!-- XXX - XXX -->
| <html>
| <head>
| <body>
#data
<!DOCTYPE html><!-- XXX - XXX
#errors
Line: 1 Col: 29 Unexpected end of file in comment (-)
#document
| <!DOCTYPE html>
| <!-- XXX - XXX -->
| <html>
| <head>
| <body>
#data
<!DOCTYPE html><!-- XXX - XXX - XXX -->
#errors
#document
| <!DOCTYPE html>
| <!-- XXX - XXX - XXX -->
| <html>
| <head>
| <body>
#data
<isindex test=x name=x>
#errors
Line: 1 Col: 23 Unexpected start tag (isindex). Expected DOCTYPE.
Line: 1 Col: 23 Unexpected start tag isindex. Don't use it!
#document
| <html>
| <head>
| <body>
| <form>
| <hr>
| <label>
| "This is a searchable index. Enter search keywords: "
| <input>
| name="isindex"
| test="x"
| <hr>
#data
test
test
#errors
Line: 2 Col: 4 Unexpected non-space characters. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| "test
test"
#data
<!DOCTYPE html><body><title>test</body></title>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <title>
| "test</body>"
#data
<!DOCTYPE html><body><title>X</title><meta name=z><link rel=foo><style>
x { content:"</style" } </style>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <title>
| "X"
| <meta>
| name="z"
| <link>
| rel="foo"
| <style>
| "
x { content:"</style" } "
#data
<!DOCTYPE html><select><optgroup></optgroup></select>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <optgroup>
#data
#errors
Line: 2 Col: 1 Unexpected End of file. Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
#data
<!DOCTYPE html> <html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<!DOCTYPE html><script>
</script> <title>x</title> </head>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <script>
| "
"
| " "
| <title>
| "x"
| " "
| <body>
#data
<!DOCTYPE html><html><body><html id=x>
#errors
Line: 1 Col: 38 html needs to be the first start tag.
#document
| <!DOCTYPE html>
| <html>
| id="x"
| <head>
| <body>
#data
<!DOCTYPE html>X</body><html id="x">
#errors
Line: 1 Col: 36 Unexpected start tag token (html) in the after body phase.
Line: 1 Col: 36 html needs to be the first start tag.
#document
| <!DOCTYPE html>
| <html>
| id="x"
| <head>
| <body>
| "X"
#data
<!DOCTYPE html><head><html id=x>
#errors
Line: 1 Col: 32 html needs to be the first start tag.
#document
| <!DOCTYPE html>
| <html>
| id="x"
| <head>
| <body>
#data
<!DOCTYPE html>X</html>X
#errors
Line: 1 Col: 24 Unexpected non-space characters in the after body phase.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "XX"
#data
<!DOCTYPE html>X</html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X "
#data
<!DOCTYPE html>X</html><p>X
#errors
Line: 1 Col: 26 Unexpected start tag (p).
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
| <p>
| "X"
#data
<!DOCTYPE html>X<p/x/y/z>
#errors
Line: 1 Col: 19 Expected a > after the /.
Line: 1 Col: 21 Solidus (/) incorrectly placed in tag.
Line: 1 Col: 23 Solidus (/) incorrectly placed in tag.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
| <p>
| x=""
| y=""
| z=""
#data
<!DOCTYPE html><!--x--
#errors
Line: 1 Col: 22 Unexpected end of file in comment (--).
#document
| <!DOCTYPE html>
| <!-- x -->
| <html>
| <head>
| <body>
#data
<!DOCTYPE html><table><tr><td></p></table>
#errors
Line: 1 Col: 34 Unexpected end tag (p). Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <p>
#data
<!DOCTYPE <!DOCTYPE HTML>><!--<!--x-->-->
#errors
Line: 1 Col: 20 Expected space or '>'. Got ''
Line: 1 Col: 25 Erroneous DOCTYPE.
Line: 1 Col: 35 Unexpected character in comment found.
#document
| <!DOCTYPE <!doctype>
| <html>
| <head>
| <body>
| ">"
| <!-- <!--x -->
| "-->"
#data
<!doctype html><div><form></form><div></div></div>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <div>
| <form>
| <div>

View File

@ -0,0 +1,455 @@
#data
<!doctype html><p><button><button>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <button>
#data
<!doctype html><p><button><address>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <address>
#data
<!doctype html><p><button><blockquote>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <blockquote>
#data
<!doctype html><p><button><menu>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <menu>
#data
<!doctype html><p><button><p>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <p>
#data
<!doctype html><p><button><ul>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <ul>
#data
<!doctype html><p><button><h1>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <h1>
#data
<!doctype html><p><button><h6>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <h6>
#data
<!doctype html><p><button><listing>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <listing>
#data
<!doctype html><p><button><pre>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <pre>
#data
<!doctype html><p><button><form>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <form>
#data
<!doctype html><p><button><li>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <li>
#data
<!doctype html><p><button><dd>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <dd>
#data
<!doctype html><p><button><dt>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <dt>
#data
<!doctype html><p><button><plaintext>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <plaintext>
#data
<!doctype html><p><button><table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <table>
#data
<!doctype html><p><button><hr>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <hr>
#data
<!doctype html><p><button><xmp>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <xmp>
#data
<!doctype html><p><button></p>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <button>
| <p>
#data
<!doctype html><address><button></address>a
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <address>
| <button>
| "a"
#data
<!doctype html><address><button></address>a
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <address>
| <button>
| "a"
#data
<p><table></p>
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <p>
| <table>
#data
<!doctype html><svg>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
#data
<!doctype html><p><figcaption>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <figcaption>
#data
<!doctype html><p><summary>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <summary>
#data
<!doctype html><form><table><form>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <form>
| <table>
#data
<!doctype html><table><form><form>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <form>
#data
<!doctype html><table><form></table><form>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <form>
#data
<!doctype html><svg><foreignObject><p>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg foreignObject>
| <p>
#data
<!doctype html><svg><title>abc
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg title>
| "abc"
#data
<option><span><option>
#errors
#document
| <html>
| <head>
| <body>
| <option>
| <span>
| <option>
#data
<option><option>
#errors
#document
| <html>
| <head>
| <body>
| <option>
| <option>
#data
<math><annotation-xml><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| <div>
#data
<math><annotation-xml encoding="application/svg+xml"><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding="application/svg+xml"
| <div>
#data
<math><annotation-xml encoding="application/xhtml+xml"><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding="application/xhtml+xml"
| <div>
#data
<math><annotation-xml encoding="aPPlication/xhtmL+xMl"><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding="aPPlication/xhtmL+xMl"
| <div>
#data
<math><annotation-xml encoding="text/html"><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding="text/html"
| <div>
#data
<math><annotation-xml encoding="Text/htmL"><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding="Text/htmL"
| <div>
#data
<math><annotation-xml encoding=" text/html "><div>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| encoding=" text/html "
| <div>

View File

@ -0,0 +1,221 @@
#data
<svg><![CDATA[foo]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "foo"
#data
<math><![CDATA[foo]]>
#errors
#document
| <html>
| <head>
| <body>
| <math math>
| "foo"
#data
<div><![CDATA[foo]]>
#errors
#document
| <html>
| <head>
| <body>
| <div>
| <!-- [CDATA[foo]] -->
#data
<svg><![CDATA[foo
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "foo"
#data
<svg><![CDATA[foo
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "foo"
#data
<svg><![CDATA[
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
#data
<svg><![CDATA[]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
#data
<svg><![CDATA[]] >]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "]] >"
#data
<svg><![CDATA[]] >]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "]] >"
#data
<svg><![CDATA[]]
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "]]"
#data
<svg><![CDATA[]
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "]"
#data
<svg><![CDATA[]>a
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "]>a"
#data
<svg><foreignObject><div><![CDATA[foo]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| <svg foreignObject>
| <div>
| <!-- [CDATA[foo]] -->
#data
<svg><![CDATA[<svg>]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>"
#data
<svg><![CDATA[</svg>a]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "</svg>a"
#data
<svg><![CDATA[<svg>a
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>a"
#data
<svg><![CDATA[</svg>a
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "</svg>a"
#data
<svg><![CDATA[<svg>]]><path>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>"
| <svg path>
#data
<svg><![CDATA[<svg>]]></path>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>"
#data
<svg><![CDATA[<svg>]]><!--path-->
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>"
| <!-- path -->
#data
<svg><![CDATA[<svg>]]>path
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<svg>path"
#data
<svg><![CDATA[<!--svg-->]]>
#errors
#document
| <html>
| <head>
| <body>
| <svg svg>
| "<!--svg-->"

View File

@ -0,0 +1,157 @@
#data
<a><b><big><em><strong><div>X</a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <b>
| <big>
| <em>
| <strong>
| <big>
| <em>
| <strong>
| <div>
| <a>
| "X"
#data
<a><b><div id=1><div id=2><div id=3><div id=4><div id=5><div id=6><div id=7><div id=8>A</a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <b>
| <b>
| <div>
| id="1"
| <a>
| <div>
| id="2"
| <a>
| <div>
| id="3"
| <a>
| <div>
| id="4"
| <a>
| <div>
| id="5"
| <a>
| <div>
| id="6"
| <a>
| <div>
| id="7"
| <a>
| <div>
| id="8"
| <a>
| "A"
#data
<a><b><div id=1><div id=2><div id=3><div id=4><div id=5><div id=6><div id=7><div id=8><div id=9>A</a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <b>
| <b>
| <div>
| id="1"
| <a>
| <div>
| id="2"
| <a>
| <div>
| id="3"
| <a>
| <div>
| id="4"
| <a>
| <div>
| id="5"
| <a>
| <div>
| id="6"
| <a>
| <div>
| id="7"
| <a>
| <div>
| id="8"
| <a>
| <div>
| id="9"
| "A"
#data
<a><b><div id=1><div id=2><div id=3><div id=4><div id=5><div id=6><div id=7><div id=8><div id=9><div id=10>A</a>
#errors
#document
| <html>
| <head>
| <body>
| <a>
| <b>
| <b>
| <div>
| id="1"
| <a>
| <div>
| id="2"
| <a>
| <div>
| id="3"
| <a>
| <div>
| id="4"
| <a>
| <div>
| id="5"
| <a>
| <div>
| id="6"
| <a>
| <div>
| id="7"
| <a>
| <div>
| id="8"
| <a>
| <div>
| id="9"
| <div>
| id="10"
| "A"
#data
<cite><b><cite><i><cite><i><cite><i><div>X</b>TEST
#errors
Line: 1 Col: 6 Unexpected start tag (cite). Expected DOCTYPE.
Line: 1 Col: 46 End tag (b) violates step 1, paragraph 3 of the adoption agency algorithm.
Line: 1 Col: 50 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <cite>
| <b>
| <cite>
| <i>
| <cite>
| <i>
| <cite>
| <i>
| <i>
| <i>
| <div>
| <b>
| "X"
| "TEST"

View File

@ -0,0 +1,155 @@
#data
<p><font size=4><font color=red><font size=4><font size=4><font size=4><font size=4><font size=4><font color=red><p>X
#errors
3: Start tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
116: Unclosed elements.
117: End of file seen and there were open elements.
#document
| <html>
| <head>
| <body>
| <p>
| <font>
| size="4"
| <font>
| color="red"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| color="red"
| <p>
| <font>
| color="red"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| color="red"
| "X"
#data
<p><font size=4><font size=4><font size=4><font size=4><p>X
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <p>
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| "X"
#data
<p><font size=4><font size=4><font size=4><font size="5"><font size=4><p>X
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="5"
| <font>
| size="4"
| <p>
| <font>
| size="4"
| <font>
| size="4"
| <font>
| size="5"
| <font>
| size="4"
| "X"
#data
<p><font size=4 id=a><font size=4 id=b><font size=4><font size=4><p>X
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <font>
| id="a"
| size="4"
| <font>
| id="b"
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| <p>
| <font>
| id="a"
| size="4"
| <font>
| id="b"
| size="4"
| <font>
| size="4"
| <font>
| size="4"
| "X"
#data
<p><b id=a><b id=a><b id=a><b><object><b id=a><b id=a>X</object><p>Y
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <b>
| id="a"
| <b>
| id="a"
| <b>
| id="a"
| <b>
| <object>
| <b>
| id="a"
| <b>
| id="a"
| "X"
| <p>
| <b>
| id="a"
| <b>
| id="a"
| <b>
| id="a"
| <b>
| "Y"

View File

@ -0,0 +1,79 @@
#data
<!DOCTYPE html>&NotEqualTilde;
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "≂̸"
#data
<!DOCTYPE html>&NotEqualTilde;A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "≂̸A"
#data
<!DOCTYPE html>&ThickSpace;
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| ""
#data
<!DOCTYPE html>&ThickSpace;A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "A"
#data
<!DOCTYPE html>&NotSubset;
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "⊂⃒"
#data
<!DOCTYPE html>&NotSubset;A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "⊂⃒A"
#data
<!DOCTYPE html>&Gopf;
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "𝔾"
#data
<!DOCTYPE html>&Gopf;A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "𝔾A"

View File

@ -0,0 +1,219 @@
#data
<!DOCTYPE html><body><foo>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <foo>
| "A"
#data
<!DOCTYPE html><body><area>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <area>
| "A"
#data
<!DOCTYPE html><body><base>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <base>
| "A"
#data
<!DOCTYPE html><body><basefont>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <basefont>
| "A"
#data
<!DOCTYPE html><body><bgsound>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <bgsound>
| "A"
#data
<!DOCTYPE html><body><br>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <br>
| "A"
#data
<!DOCTYPE html><body><col>A
#errors
26: Stray start tag “col”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "A"
#data
<!DOCTYPE html><body><command>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <command>
| "A"
#data
<!DOCTYPE html><body><embed>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <embed>
| "A"
#data
<!DOCTYPE html><body><frame>A
#errors
26: Stray start tag “frame”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "A"
#data
<!DOCTYPE html><body><hr>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <hr>
| "A"
#data
<!DOCTYPE html><body><img>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <img>
| "A"
#data
<!DOCTYPE html><body><input>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <input>
| "A"
#data
<!DOCTYPE html><body><keygen>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <keygen>
| "A"
#data
<!DOCTYPE html><body><link>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <link>
| "A"
#data
<!DOCTYPE html><body><meta>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <meta>
| "A"
#data
<!DOCTYPE html><body><param>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <param>
| "A"
#data
<!DOCTYPE html><body><source>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <source>
| "A"
#data
<!DOCTYPE html><body><track>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <track>
| "A"
#data
<!DOCTYPE html><body><wbr>A
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <wbr>
| "A"

View File

@ -0,0 +1,313 @@
#data
<!DOCTYPE html><body><a href='#1'><nobr>1<nobr></a><br><a href='#2'><nobr>2<nobr></a><br><a href='#3'><nobr>3<nobr></a>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <a>
| href="#1"
| <nobr>
| "1"
| <nobr>
| <nobr>
| <br>
| <a>
| href="#2"
| <a>
| href="#2"
| <nobr>
| "2"
| <nobr>
| <nobr>
| <br>
| <a>
| href="#3"
| <a>
| href="#3"
| <nobr>
| "3"
| <nobr>
#data
<!DOCTYPE html><body><b><nobr>1<nobr></b><i><nobr>2<nobr></i>3
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <nobr>
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
| <nobr>
| <nobr>
| "3"
#data
<!DOCTYPE html><body><b><nobr>1<table><nobr></b><i><nobr>2<nobr></i>3
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
| <nobr>
| <nobr>
| "3"
| <table>
#data
<!DOCTYPE html><body><b><nobr>1<table><tr><td><nobr></b><i><nobr>2<nobr></i>3
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <table>
| <tbody>
| <tr>
| <td>
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
| <nobr>
| <nobr>
| "3"
#data
<!DOCTYPE html><body><b><nobr>1<div><nobr></b><i><nobr>2<nobr></i>3
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <div>
| <b>
| <nobr>
| <nobr>
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
| <nobr>
| <nobr>
| "3"
#data
<!DOCTYPE html><body><b><nobr>1<nobr></b><div><i><nobr>2<nobr></i>3
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <nobr>
| <div>
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
| <nobr>
| <nobr>
| "3"
#data
<!DOCTYPE html><body><b><nobr>1<nobr><ins></b><i><nobr>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <nobr>
| <ins>
| <nobr>
| <i>
| <i>
| <nobr>
#data
<!DOCTYPE html><body><b><nobr>1<ins><nobr></b><i>2
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| <nobr>
| "1"
| <ins>
| <nobr>
| <nobr>
| <i>
| "2"
#data
<!DOCTYPE html><body><b>1<nobr></b><i><nobr>2</i>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <b>
| "1"
| <nobr>
| <nobr>
| <i>
| <i>
| <nobr>
| "2"
#data
<p><code x</code></p>
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <code>
| code=""
| x<=""
| <code>
| code=""
| x<=""
| "
"
#data
<!DOCTYPE html><svg><foreignObject><p><i></p>a
#errors
45: End tag “p” seen, but there were open elements.
41: Unclosed element “i”.
46: End of file seen and there were open elements.
35: Unclosed element “foreignObject”.
20: Unclosed element “svg”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <svg svg>
| <svg foreignObject>
| <p>
| <i>
| <i>
| "a"
#data
<!DOCTYPE html><table><tr><td><svg><foreignObject><p><i></p>a
#errors
56: End tag “p” seen, but there were open elements.
52: Unclosed element “i”.
57: End of file seen and there were open elements.
46: Unclosed element “foreignObject”.
31: Unclosed element “svg”.
22: Unclosed element “table”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <svg svg>
| <svg foreignObject>
| <p>
| <i>
| <i>
| "a"
#data
<!DOCTYPE html><math><mtext><p><i></p>a
#errors
38: End tag “p” seen, but there were open elements.
34: Unclosed element “i”.
39: End of file in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mtext>
| <p>
| <i>
| <i>
| "a"
#data
<!DOCTYPE html><table><tr><td><math><mtext><p><i></p>a
#errors
53: End tag “p” seen, but there were open elements.
49: Unclosed element “i”.
54: End of file in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <math math>
| <math mtext>
| <p>
| <i>
| <i>
| "a"
#data
<!DOCTYPE html><body><div><!/div>a
#errors
29: Bogus comment.
34: End of file seen and there were open elements.
26: Unclosed element “div”.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <div>
| <!-- /div -->
| "a"

View File

@ -0,0 +1,305 @@
#data
<head></head><style></style>
#errors
Line: 1 Col: 6 Unexpected start tag (head). Expected DOCTYPE.
Line: 1 Col: 20 Unexpected start tag (style) that can be in head. Moved.
#document
| <html>
| <head>
| <style>
| <body>
#data
<head></head><script></script>
#errors
Line: 1 Col: 6 Unexpected start tag (head). Expected DOCTYPE.
Line: 1 Col: 21 Unexpected start tag (script) that can be in head. Moved.
#document
| <html>
| <head>
| <script>
| <body>
#data
<head></head><!-- --><style></style><!-- --><script></script>
#errors
Line: 1 Col: 6 Unexpected start tag (head). Expected DOCTYPE.
Line: 1 Col: 28 Unexpected start tag (style) that can be in head. Moved.
#document
| <html>
| <head>
| <style>
| <script>
| <!-- -->
| <!-- -->
| <body>
#data
<head></head><!-- -->x<style></style><!-- --><script></script>
#errors
Line: 1 Col: 6 Unexpected start tag (head). Expected DOCTYPE.
#document
| <html>
| <head>
| <!-- -->
| <body>
| "x"
| <style>
| <!-- -->
| <script>
#data
<!DOCTYPE html><html><head></head><body><pre>
</pre></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
#data
<!DOCTYPE html><html><head></head><body><pre>
foo</pre></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "foo"
#data
<!DOCTYPE html><html><head></head><body><pre>
foo</pre></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "
foo"
#data
<!DOCTYPE html><html><head></head><body><pre>
foo
</pre></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "foo
"
#data
<!DOCTYPE html><html><head></head><body><pre>x</pre><span>
</span></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "x"
| <span>
| "
"
#data
<!DOCTYPE html><html><head></head><body><pre>x
y</pre></body></html>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "x
y"
#data
<!DOCTYPE html><html><head></head><body><pre>x<div>
y</pre></body></html>
#errors
Line: 2 Col: 7 End tag (pre) seen too early. Expected other end tag.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "x"
| <div>
| "
y"
#data
<!DOCTYPE html><pre>&#x0a;&#x0a;A</pre>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <pre>
| "
A"
#data
<!DOCTYPE html><HTML><META><HEAD></HEAD></HTML>
#errors
Line: 1 Col: 33 Unexpected start tag head in existing head. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <meta>
| <body>
#data
<!DOCTYPE html><HTML><HEAD><head></HEAD></HTML>
#errors
Line: 1 Col: 33 Unexpected start tag head in existing head. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<textarea>foo<span>bar</span><i>baz
#errors
Line: 1 Col: 10 Unexpected start tag (textarea). Expected DOCTYPE.
Line: 1 Col: 35 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <textarea>
| "foo<span>bar</span><i>baz"
#data
<title>foo<span>bar</em><i>baz
#errors
Line: 1 Col: 7 Unexpected start tag (title). Expected DOCTYPE.
Line: 1 Col: 30 Unexpected end of file. Expected end tag (title).
#document
| <html>
| <head>
| <title>
| "foo<span>bar</em><i>baz"
| <body>
#data
<!DOCTYPE html><textarea>
</textarea>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <textarea>
#data
<!DOCTYPE html><textarea>
foo</textarea>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <textarea>
| "foo"
#data
<!DOCTYPE html><textarea>
foo</textarea>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <textarea>
| "
foo"
#data
<!DOCTYPE html><html><head></head><body><ul><li><div><p><li></ul></body></html>
#errors
Line: 1 Col: 60 Missing end tag (div, li).
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <ul>
| <li>
| <div>
| <p>
| <li>
#data
<!doctype html><nobr><nobr><nobr>
#errors
Line: 1 Col: 27 Unexpected start tag (nobr) implies end tag (nobr).
Line: 1 Col: 33 Unexpected start tag (nobr) implies end tag (nobr).
Line: 1 Col: 33 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <nobr>
| <nobr>
| <nobr>
#data
<!doctype html><nobr><nobr></nobr><nobr>
#errors
Line: 1 Col: 27 Unexpected start tag (nobr) implies end tag (nobr).
Line: 1 Col: 40 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <nobr>
| <nobr>
| <nobr>
#data
<!doctype html><html><body><p><table></table></body></html>
#errors
Not known
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <table>
#data
<p><table></table>
#errors
Not known
#document
| <html>
| <head>
| <body>
| <p>
| <table>

View File

@ -0,0 +1,59 @@
#data
direct div content
#errors
#document-fragment
div
#document
| "direct div content"
#data
direct textarea content
#errors
#document-fragment
textarea
#document
| "direct textarea content"
#data
textarea content with <em>pseudo</em> <foo>markup
#errors
#document-fragment
textarea
#document
| "textarea content with <em>pseudo</em> <foo>markup"
#data
this is &#x0043;DATA inside a <style> element
#errors
#document-fragment
style
#document
| "this is &#x0043;DATA inside a <style> element"
#data
</plaintext>
#errors
#document-fragment
plaintext
#document
| "</plaintext>"
#data
setting html's innerHTML
#errors
Line: 1 Col: 24 Unexpected EOF in inner html mode.
#document-fragment
html
#document
| <head>
| <body>
| "setting html's innerHTML"
#data
<title>setting head's innerHTML</title>
#errors
#document-fragment
head
#document
| <title>
| "setting head's innerHTML"

View File

@ -0,0 +1,191 @@
#data
<style> <!-- </style>x
#errors
Line: 1 Col: 7 Unexpected start tag (style). Expected DOCTYPE.
Line: 1 Col: 22 Unexpected end of file. Expected end tag (style).
#document
| <html>
| <head>
| <style>
| " <!-- "
| <body>
| "x"
#data
<style> <!-- </style> --> </style>x
#errors
Line: 1 Col: 7 Unexpected start tag (style). Expected DOCTYPE.
#document
| <html>
| <head>
| <style>
| " <!-- "
| " "
| <body>
| "--> x"
#data
<style> <!--> </style>x
#errors
Line: 1 Col: 7 Unexpected start tag (style). Expected DOCTYPE.
#document
| <html>
| <head>
| <style>
| " <!--> "
| <body>
| "x"
#data
<style> <!---> </style>x
#errors
Line: 1 Col: 7 Unexpected start tag (style). Expected DOCTYPE.
#document
| <html>
| <head>
| <style>
| " <!---> "
| <body>
| "x"
#data
<iframe> <!---> </iframe>x
#errors
Line: 1 Col: 8 Unexpected start tag (iframe). Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| <iframe>
| " <!---> "
| "x"
#data
<iframe> <!--- </iframe>->x</iframe> --> </iframe>x
#errors
Line: 1 Col: 8 Unexpected start tag (iframe). Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| <iframe>
| " <!--- "
| "->x --> x"
#data
<script> <!-- </script> --> </script>x
#errors
Line: 1 Col: 8 Unexpected start tag (script). Expected DOCTYPE.
#document
| <html>
| <head>
| <script>
| " <!-- "
| " "
| <body>
| "--> x"
#data
<title> <!-- </title> --> </title>x
#errors
Line: 1 Col: 7 Unexpected start tag (title). Expected DOCTYPE.
#document
| <html>
| <head>
| <title>
| " <!-- "
| " "
| <body>
| "--> x"
#data
<textarea> <!--- </textarea>->x</textarea> --> </textarea>x
#errors
Line: 1 Col: 10 Unexpected start tag (textarea). Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| <textarea>
| " <!--- "
| "->x --> x"
#data
<style> <!</-- </style>x
#errors
Line: 1 Col: 7 Unexpected start tag (style). Expected DOCTYPE.
#document
| <html>
| <head>
| <style>
| " <!</-- "
| <body>
| "x"
#data
<p><xmp></xmp>
#errors
XXX: Unknown
#document
| <html>
| <head>
| <body>
| <p>
| <xmp>
#data
<xmp> <!-- > --> </xmp>
#errors
Line: 1 Col: 5 Unexpected start tag (xmp). Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| <xmp>
| " <!-- > --> "
#data
<title>&amp;</title>
#errors
Line: 1 Col: 7 Unexpected start tag (title). Expected DOCTYPE.
#document
| <html>
| <head>
| <title>
| "&"
| <body>
#data
<title><!--&amp;--></title>
#errors
Line: 1 Col: 7 Unexpected start tag (title). Expected DOCTYPE.
#document
| <html>
| <head>
| <title>
| "<!--&-->"
| <body>
#data
<title><!--</title>
#errors
Line: 1 Col: 7 Unexpected start tag (title). Expected DOCTYPE.
Line: 1 Col: 19 Unexpected end of file. Expected end tag (title).
#document
| <html>
| <head>
| <title>
| "<!--"
| <body>
#data
<noscript><!--</noscript>--></noscript>
#errors
Line: 1 Col: 10 Unexpected start tag (noscript). Expected DOCTYPE.
#document
| <html>
| <head>
| <noscript>
| "<!--"
| <body>
| "-->"

View File

@ -0,0 +1,663 @@
#data
<!doctype html></head> <head>
#errors
Line: 1 Col: 29 Unexpected start tag head. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| " "
| <body>
#data
<!doctype html><form><div></form><div>
#errors
33: End tag "form" seen but there were unclosed elements.
38: End of file seen and there were open elements.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <form>
| <div>
| <div>
#data
<!doctype html><title>&amp;</title>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <title>
| "&"
| <body>
#data
<!doctype html><title><!--&amp;--></title>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <title>
| "<!--&-->"
| <body>
#data
<!doctype>
#errors
Line: 1 Col: 9 No space after literal string 'DOCTYPE'.
Line: 1 Col: 10 Unexpected > character. Expected DOCTYPE name.
Line: 1 Col: 10 Erroneous DOCTYPE.
#document
| <!DOCTYPE >
| <html>
| <head>
| <body>
#data
<!---x
#errors
Line: 1 Col: 6 Unexpected end of file in comment.
Line: 1 Col: 6 Unexpected End of file. Expected DOCTYPE.
#document
| <!-- -x -->
| <html>
| <head>
| <body>
#data
<body>
<div>
#errors
Line: 1 Col: 6 Unexpected start tag (body).
Line: 2 Col: 5 Expected closing tag. Unexpected end of file.
#document-fragment
div
#document
| "
"
| <div>
#data
<frameset></frameset>
foo
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 2 Col: 3 Unexpected non-space characters in the after frameset phase. Ignored.
#document
| <html>
| <head>
| <frameset>
| "
"
#data
<frameset></frameset>
<noframes>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 2 Col: 10 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <frameset>
| "
"
| <noframes>
#data
<frameset></frameset>
<div>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 2 Col: 5 Unexpected start tag (div) in the after frameset phase. Ignored.
#document
| <html>
| <head>
| <frameset>
| "
"
#data
<frameset></frameset>
</html>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
#document
| <html>
| <head>
| <frameset>
| "
"
#data
<frameset></frameset>
</div>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 2 Col: 6 Unexpected end tag (div) in the after frameset phase. Ignored.
#document
| <html>
| <head>
| <frameset>
| "
"
#data
<form><form>
#errors
Line: 1 Col: 6 Unexpected start tag (form). Expected DOCTYPE.
Line: 1 Col: 12 Unexpected start tag (form).
Line: 1 Col: 12 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <form>
#data
<button><button>
#errors
Line: 1 Col: 8 Unexpected start tag (button). Expected DOCTYPE.
Line: 1 Col: 16 Unexpected start tag (button) implies end tag (button).
Line: 1 Col: 16 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <button>
| <button>
#data
<table><tr><td></th>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 20 Unexpected end tag (th). Ignored.
Line: 1 Col: 20 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
#data
<table><caption><td>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 20 Unexpected end tag (td). Ignored.
Line: 1 Col: 20 Unexpected table cell start tag (td) in the table body phase.
Line: 1 Col: 20 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
| <tbody>
| <tr>
| <td>
#data
<table><caption><div>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 21 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
| <div>
#data
</caption><div>
#errors
Line: 1 Col: 10 Unexpected end tag (caption). Ignored.
Line: 1 Col: 15 Expected closing tag. Unexpected end of file.
#document-fragment
caption
#document
| <div>
#data
<table><caption><div></caption>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 31 Unexpected end tag (caption). Missing end tag (div).
Line: 1 Col: 31 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
| <div>
#data
<table><caption></table>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 24 Unexpected end table tag in caption. Generates implied end caption.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
#data
</table><div>
#errors
Line: 1 Col: 8 Unexpected end table tag in caption. Generates implied end caption.
Line: 1 Col: 8 Unexpected end tag (caption). Ignored.
Line: 1 Col: 13 Expected closing tag. Unexpected end of file.
#document-fragment
caption
#document
| <div>
#data
<table><caption></body></col></colgroup></html></tbody></td></tfoot></th></thead></tr>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 23 Unexpected end tag (body). Ignored.
Line: 1 Col: 29 Unexpected end tag (col). Ignored.
Line: 1 Col: 40 Unexpected end tag (colgroup). Ignored.
Line: 1 Col: 47 Unexpected end tag (html). Ignored.
Line: 1 Col: 55 Unexpected end tag (tbody). Ignored.
Line: 1 Col: 60 Unexpected end tag (td). Ignored.
Line: 1 Col: 68 Unexpected end tag (tfoot). Ignored.
Line: 1 Col: 73 Unexpected end tag (th). Ignored.
Line: 1 Col: 81 Unexpected end tag (thead). Ignored.
Line: 1 Col: 86 Unexpected end tag (tr). Ignored.
Line: 1 Col: 86 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
#data
<table><caption><div></div>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 27 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <caption>
| <div>
#data
<table><tr><td></body></caption></col></colgroup></html>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 22 Unexpected end tag (body). Ignored.
Line: 1 Col: 32 Unexpected end tag (caption). Ignored.
Line: 1 Col: 38 Unexpected end tag (col). Ignored.
Line: 1 Col: 49 Unexpected end tag (colgroup). Ignored.
Line: 1 Col: 56 Unexpected end tag (html). Ignored.
Line: 1 Col: 56 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
#data
</table></tbody></tfoot></thead></tr><div>
#errors
Line: 1 Col: 8 Unexpected end tag (table). Ignored.
Line: 1 Col: 16 Unexpected end tag (tbody). Ignored.
Line: 1 Col: 24 Unexpected end tag (tfoot). Ignored.
Line: 1 Col: 32 Unexpected end tag (thead). Ignored.
Line: 1 Col: 37 Unexpected end tag (tr). Ignored.
Line: 1 Col: 42 Expected closing tag. Unexpected end of file.
#document-fragment
td
#document
| <div>
#data
<table><colgroup>foo
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 20 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 20 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| "foo"
| <table>
| <colgroup>
#data
foo<col>
#errors
Line: 1 Col: 3 Unexpected end tag (colgroup). Ignored.
#document-fragment
colgroup
#document
| <col>
#data
<table><colgroup></col>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 23 This element (col) has no end tag.
Line: 1 Col: 23 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <table>
| <colgroup>
#data
<frameset><div>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 1 Col: 15 Unexpected start tag token (div) in the frameset phase. Ignored.
Line: 1 Col: 15 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <frameset>
#data
</frameset><frame>
#errors
Line: 1 Col: 11 Unexpected end tag token (frameset) in the frameset phase (innerHTML).
#document-fragment
frameset
#document
| <frame>
#data
<frameset></div>
#errors
Line: 1 Col: 10 Unexpected start tag (frameset). Expected DOCTYPE.
Line: 1 Col: 16 Unexpected end tag token (div) in the frameset phase. Ignored.
Line: 1 Col: 16 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <frameset>
#data
</body><div>
#errors
Line: 1 Col: 7 Unexpected end tag (body). Ignored.
Line: 1 Col: 12 Expected closing tag. Unexpected end of file.
#document-fragment
body
#document
| <div>
#data
<table><tr><div>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 16 Unexpected start tag (div) in table context caused voodoo mode.
Line: 1 Col: 16 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <div>
| <table>
| <tbody>
| <tr>
#data
</tr><td>
#errors
Line: 1 Col: 5 Unexpected end tag (tr). Ignored.
#document-fragment
tr
#document
| <td>
#data
</tbody></tfoot></thead><td>
#errors
Line: 1 Col: 8 Unexpected end tag (tbody). Ignored.
Line: 1 Col: 16 Unexpected end tag (tfoot). Ignored.
Line: 1 Col: 24 Unexpected end tag (thead). Ignored.
#document-fragment
tr
#document
| <td>
#data
<table><tr><div><td>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 16 Unexpected start tag (div) in table context caused voodoo mode.
Line: 1 Col: 20 Unexpected implied end tag (div) in the table row phase.
Line: 1 Col: 20 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| <table>
| <tbody>
| <tr>
| <td>
#data
<caption><col><colgroup><tbody><tfoot><thead><tr>
#errors
Line: 1 Col: 9 Unexpected start tag (caption).
Line: 1 Col: 14 Unexpected start tag (col).
Line: 1 Col: 24 Unexpected start tag (colgroup).
Line: 1 Col: 31 Unexpected start tag (tbody).
Line: 1 Col: 38 Unexpected start tag (tfoot).
Line: 1 Col: 45 Unexpected start tag (thead).
Line: 1 Col: 49 Unexpected end of file. Expected table content.
#document-fragment
tbody
#document
| <tr>
#data
<table><tbody></thead>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 22 Unexpected end tag (thead) in the table body phase. Ignored.
Line: 1 Col: 22 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
#data
</table><tr>
#errors
Line: 1 Col: 8 Unexpected end tag (table). Ignored.
Line: 1 Col: 12 Unexpected end of file. Expected table content.
#document-fragment
tbody
#document
| <tr>
#data
<table><tbody></body></caption></col></colgroup></html></td></th></tr>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 21 Unexpected end tag (body) in the table body phase. Ignored.
Line: 1 Col: 31 Unexpected end tag (caption) in the table body phase. Ignored.
Line: 1 Col: 37 Unexpected end tag (col) in the table body phase. Ignored.
Line: 1 Col: 48 Unexpected end tag (colgroup) in the table body phase. Ignored.
Line: 1 Col: 55 Unexpected end tag (html) in the table body phase. Ignored.
Line: 1 Col: 60 Unexpected end tag (td) in the table body phase. Ignored.
Line: 1 Col: 65 Unexpected end tag (th) in the table body phase. Ignored.
Line: 1 Col: 70 Unexpected end tag (tr) in the table body phase. Ignored.
Line: 1 Col: 70 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
#data
<table><tbody></div>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 20 Unexpected end tag (div) in table context caused voodoo mode.
Line: 1 Col: 20 End tag (div) seen too early. Expected other end tag.
Line: 1 Col: 20 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
#data
<table><table>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 14 Unexpected start tag (table) implies end tag (table).
Line: 1 Col: 14 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
| <table>
#data
<table></body></caption></col></colgroup></html></tbody></td></tfoot></th></thead></tr>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 14 Unexpected end tag (body). Ignored.
Line: 1 Col: 24 Unexpected end tag (caption). Ignored.
Line: 1 Col: 30 Unexpected end tag (col). Ignored.
Line: 1 Col: 41 Unexpected end tag (colgroup). Ignored.
Line: 1 Col: 48 Unexpected end tag (html). Ignored.
Line: 1 Col: 56 Unexpected end tag (tbody). Ignored.
Line: 1 Col: 61 Unexpected end tag (td). Ignored.
Line: 1 Col: 69 Unexpected end tag (tfoot). Ignored.
Line: 1 Col: 74 Unexpected end tag (th). Ignored.
Line: 1 Col: 82 Unexpected end tag (thead). Ignored.
Line: 1 Col: 87 Unexpected end tag (tr). Ignored.
Line: 1 Col: 87 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <table>
#data
</table><tr>
#errors
Line: 1 Col: 8 Unexpected end tag (table). Ignored.
Line: 1 Col: 12 Unexpected end of file. Expected table content.
#document-fragment
table
#document
| <tbody>
| <tr>
#data
<body></body></html>
#errors
Line: 1 Col: 20 Unexpected html end tag in inner html mode.
Line: 1 Col: 20 Unexpected EOF in inner html mode.
#document-fragment
html
#document
| <head>
| <body>
#data
<html><frameset></frameset></html>
#errors
Line: 1 Col: 6 Unexpected start tag (html). Expected DOCTYPE.
#document
| <html>
| <head>
| <frameset>
| " "
#data
<!DOCTYPE html PUBLIC "-//W3C//DTD HTML 4.01//EN"><html></html>
#errors
Line: 1 Col: 50 Erroneous DOCTYPE.
Line: 1 Col: 63 Unexpected end tag (html) after the (implied) root element.
#document
| <!DOCTYPE html "-//W3C//DTD HTML 4.01//EN" "">
| <html>
| <head>
| <body>
#data
<param><frameset></frameset>
#errors
Line: 1 Col: 7 Unexpected start tag (param). Expected DOCTYPE.
Line: 1 Col: 17 Unexpected start tag (frameset).
#document
| <html>
| <head>
| <frameset>
#data
<source><frameset></frameset>
#errors
Line: 1 Col: 7 Unexpected start tag (source). Expected DOCTYPE.
Line: 1 Col: 17 Unexpected start tag (frameset).
#document
| <html>
| <head>
| <frameset>
#data
<track><frameset></frameset>
#errors
Line: 1 Col: 7 Unexpected start tag (track). Expected DOCTYPE.
Line: 1 Col: 17 Unexpected start tag (frameset).
#document
| <html>
| <head>
| <frameset>
#data
</html><frameset></frameset>
#errors
7: End tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
17: Stray “frameset” start tag.
17: “frameset” start tag seen.
#document
| <html>
| <head>
| <frameset>
#data
</body><frameset></frameset>
#errors
7: End tag seen without seeing a doctype first. Expected “<!DOCTYPE html>”.
17: Stray “frameset” start tag.
17: “frameset” start tag seen.
#document
| <html>
| <head>
| <frameset>

View File

@ -0,0 +1,390 @@
#data
<!doctype html><body><title>X</title>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <title>
| "X"
#data
<!doctype html><table><title>X</title></table>
#errors
Line: 1 Col: 29 Unexpected start tag (title) in table context caused voodoo mode.
Line: 1 Col: 38 Unexpected end tag (title) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <title>
| "X"
| <table>
#data
<!doctype html><head></head><title>X</title>
#errors
Line: 1 Col: 35 Unexpected start tag (title) that can be in head. Moved.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <title>
| "X"
| <body>
#data
<!doctype html></head><title>X</title>
#errors
Line: 1 Col: 29 Unexpected start tag (title) that can be in head. Moved.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <title>
| "X"
| <body>
#data
<!doctype html><table><meta></table>
#errors
Line: 1 Col: 28 Unexpected start tag (meta) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <meta>
| <table>
#data
<!doctype html><table>X<tr><td><table> <meta></table></table>
#errors
Line: 1 Col: 23 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 45 Unexpected start tag (meta) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
| <table>
| <tbody>
| <tr>
| <td>
| <meta>
| <table>
| " "
#data
<!doctype html><html> <head>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<!doctype html> <head>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<!doctype html><table><style> <tr>x </style> </table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <style>
| " <tr>x "
| " "
#data
<!doctype html><table><TBODY><script> <tr>x </script> </table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <script>
| " <tr>x "
| " "
#data
<!doctype html><p><applet><p>X</p></applet>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <p>
| <applet>
| <p>
| "X"
#data
<!doctype html><listing>
X</listing>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <listing>
| "X"
#data
<!doctype html><select><input>X
#errors
Line: 1 Col: 30 Unexpected input start tag in the select phase.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <input>
| "X"
#data
<!doctype html><select><select>X
#errors
Line: 1 Col: 31 Unexpected select start tag in the select phase treated as select end tag.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| "X"
#data
<!doctype html><table><input type=hidDEN></table>
#errors
Line: 1 Col: 41 Unexpected input with type hidden in table context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <input>
| type="hidDEN"
#data
<!doctype html><table>X<input type=hidDEN></table>
#errors
Line: 1 Col: 23 Unexpected non-space characters in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| "X"
| <table>
| <input>
| type="hidDEN"
#data
<!doctype html><table> <input type=hidDEN></table>
#errors
Line: 1 Col: 43 Unexpected input with type hidden in table context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| " "
| <input>
| type="hidDEN"
#data
<!doctype html><table> <input type='hidDEN'></table>
#errors
Line: 1 Col: 45 Unexpected input with type hidden in table context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| " "
| <input>
| type="hidDEN"
#data
<!doctype html><table><input type=" hidden"><input type=hidDEN></table>
#errors
Line: 1 Col: 44 Unexpected start tag (input) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <input>
| type=" hidden"
| <table>
| <input>
| type="hidDEN"
#data
<!doctype html><table><select>X<tr>
#errors
Line: 1 Col: 30 Unexpected start tag (select) in table context caused voodoo mode.
Line: 1 Col: 35 Unexpected table element start tag (trs) in the select in table phase.
Line: 1 Col: 35 Unexpected end of file. Expected table content.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| "X"
| <table>
| <tbody>
| <tr>
#data
<!doctype html><select>X</select>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| "X"
#data
<!DOCTYPE hTmL><html></html>
#errors
Line: 1 Col: 28 Unexpected end tag (html) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<!DOCTYPE HTML><html></html>
#errors
Line: 1 Col: 28 Unexpected end tag (html) after the (implied) root element.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
#data
<body>X</body></body>
#errors
Line: 1 Col: 21 Unexpected end tag token (body) in the after body phase.
Line: 1 Col: 21 Unexpected EOF in inner html mode.
#document-fragment
html
#document
| <head>
| <body>
| "X"
#data
<div><p>a</x> b
#errors
Line: 1 Col: 5 Unexpected start tag (div). Expected DOCTYPE.
Line: 1 Col: 13 Unexpected end tag (x). Ignored.
Line: 1 Col: 15 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| <p>
| "a b"
#data
<table><tr><td><code></code> </table>
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
#document
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <code>
| " "
#data
<table><b><tr><td>aaa</td></tr>bbb</table>ccc
#errors
XXX: Fix me
#document
| <html>
| <head>
| <body>
| <b>
| <b>
| "bbb"
| <table>
| <tbody>
| <tr>
| <td>
| "aaa"
| <b>
| "ccc"
#data
A<table><tr> B</tr> B</table>
#errors
XXX: Fix me
#document
| <html>
| <head>
| <body>
| "A B B"
| <table>
| <tbody>
| <tr>
#data
A<table><tr> B</tr> </em>C</table>
#errors
XXX: Fix me
#document
| <html>
| <head>
| <body>
| "A BC"
| <table>
| <tbody>
| <tr>
| " "
#data
<select><keygen>
#errors
Not known
#document
| <html>
| <head>
| <body>
| <select>
| <keygen>

View File

@ -0,0 +1,148 @@
#data
<div>
<div></div>
</span>x
#errors
Line: 1 Col: 5 Unexpected start tag (div). Expected DOCTYPE.
Line: 3 Col: 7 Unexpected end tag (span). Ignored.
Line: 3 Col: 8 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| "
"
| <div>
| "
x"
#data
<div>x<div></div>
</span>x
#errors
Line: 1 Col: 5 Unexpected start tag (div). Expected DOCTYPE.
Line: 2 Col: 7 Unexpected end tag (span). Ignored.
Line: 2 Col: 8 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| "x"
| <div>
| "
x"
#data
<div>x<div></div>x</span>x
#errors
Line: 1 Col: 5 Unexpected start tag (div). Expected DOCTYPE.
Line: 1 Col: 25 Unexpected end tag (span). Ignored.
Line: 1 Col: 26 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| "x"
| <div>
| "xx"
#data
<div>x<div></div>y</span>z
#errors
Line: 1 Col: 5 Unexpected start tag (div). Expected DOCTYPE.
Line: 1 Col: 25 Unexpected end tag (span). Ignored.
Line: 1 Col: 26 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <div>
| "x"
| <div>
| "yz"
#data
<table><div>x<div></div>x</span>x
#errors
Line: 1 Col: 7 Unexpected start tag (table). Expected DOCTYPE.
Line: 1 Col: 12 Unexpected start tag (div) in table context caused voodoo mode.
Line: 1 Col: 18 Unexpected start tag (div) in table context caused voodoo mode.
Line: 1 Col: 24 Unexpected end tag (div) in table context caused voodoo mode.
Line: 1 Col: 32 Unexpected end tag (span) in table context caused voodoo mode.
Line: 1 Col: 32 Unexpected end tag (span). Ignored.
Line: 1 Col: 33 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| <div>
| "x"
| <div>
| "xx"
| <table>
#data
x<table>x
#errors
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
Line: 1 Col: 9 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 9 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| "xx"
| <table>
#data
x<table><table>x
#errors
Line: 1 Col: 1 Unexpected non-space characters. Expected DOCTYPE.
Line: 1 Col: 15 Unexpected start tag (table) implies end tag (table).
Line: 1 Col: 16 Unexpected non-space characters in table context caused voodoo mode.
Line: 1 Col: 16 Unexpected end of file. Expected table content.
#document
| <html>
| <head>
| <body>
| "x"
| <table>
| "x"
| <table>
#data
<b>a<div></div><div></b>y
#errors
Line: 1 Col: 3 Unexpected start tag (b). Expected DOCTYPE.
Line: 1 Col: 24 End tag (b) violates step 1, paragraph 3 of the adoption agency algorithm.
Line: 1 Col: 25 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <b>
| "a"
| <div>
| <div>
| <b>
| "y"
#data
<a><div><p></a>
#errors
Line: 1 Col: 3 Unexpected start tag (a). Expected DOCTYPE.
Line: 1 Col: 15 End tag (a) violates step 1, paragraph 3 of the adoption agency algorithm.
Line: 1 Col: 15 End tag (a) violates step 1, paragraph 3 of the adoption agency algorithm.
Line: 1 Col: 15 Expected closing tag. Unexpected end of file.
#document
| <html>
| <head>
| <body>
| <a>
| <div>
| <a>
| <p>
| <a>

View File

@ -0,0 +1,457 @@
#data
<!DOCTYPE html><math></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
#data
<!DOCTYPE html><body><math></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
#data
<!DOCTYPE html><math><mi>
#errors
25: End of file in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
#data
<!DOCTYPE html><math><annotation-xml><svg><u>
#errors
45: HTML start tag “u” in a foreign namespace context.
45: End of file seen and there were open elements.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math annotation-xml>
| <svg svg>
| <u>
#data
<!DOCTYPE html><body><select><math></math></select>
#errors
Line: 1 Col: 35 Unexpected start tag token (math) in the select phase. Ignored.
Line: 1 Col: 42 Unexpected end tag (math) in the select phase. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
#data
<!DOCTYPE html><body><select><option><math></math></option></select>
#errors
Line: 1 Col: 43 Unexpected start tag token (math) in the select phase. Ignored.
Line: 1 Col: 50 Unexpected end tag (math) in the select phase. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| <option>
#data
<!DOCTYPE html><body><table><math></math></table>
#errors
Line: 1 Col: 34 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 41 Unexpected end tag (math) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <table>
#data
<!DOCTYPE html><body><table><math><mi>foo</mi></math></table>
#errors
Line: 1 Col: 34 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 46 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 53 Unexpected end tag (math) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <table>
#data
<!DOCTYPE html><body><table><math><mi>foo</mi><mi>bar</mi></math></table>
#errors
Line: 1 Col: 34 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 46 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 58 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 65 Unexpected end tag (math) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <table>
#data
<!DOCTYPE html><body><table><tbody><math><mi>foo</mi><mi>bar</mi></math></tbody></table>
#errors
Line: 1 Col: 41 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 53 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 65 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 72 Unexpected end tag (math) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <table>
| <tbody>
#data
<!DOCTYPE html><body><table><tbody><tr><math><mi>foo</mi><mi>bar</mi></math></tr></tbody></table>
#errors
Line: 1 Col: 45 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 57 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 69 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 76 Unexpected end tag (math) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <table>
| <tbody>
| <tr>
#data
<!DOCTYPE html><body><table><tbody><tr><td><math><mi>foo</mi><mi>bar</mi></math></td></tr></tbody></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
#data
<!DOCTYPE html><body><table><tbody><tr><td><math><mi>foo</mi><mi>bar</mi></math><p>baz</td></tr></tbody></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body><table><caption><math><mi>foo</mi><mi>bar</mi></math><p>baz</caption></table>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body><table><caption><math><mi>foo</mi><mi>bar</mi><p>baz</table><p>quux
#errors
Line: 1 Col: 70 HTML start tag "p" in a foreign namespace context.
Line: 1 Col: 81 Unexpected end table tag in caption. Generates implied end caption.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><caption><math><mi>foo</mi><mi>bar</mi>baz</table><p>quux
#errors
Line: 1 Col: 78 Unexpected end table tag in caption. Generates implied end caption.
Line: 1 Col: 78 Unexpected end tag (caption). Missing end tag (math).
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <caption>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| "baz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><colgroup><math><mi>foo</mi><mi>bar</mi><p>baz</table><p>quux
#errors
Line: 1 Col: 44 Unexpected start tag (math) in table context caused voodoo mode.
Line: 1 Col: 56 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 68 Unexpected end tag (mi) in table context caused voodoo mode.
Line: 1 Col: 71 HTML start tag "p" in a foreign namespace context.
Line: 1 Col: 71 Unexpected start tag (p) in table context caused voodoo mode.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
| <table>
| <colgroup>
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><tr><td><select><math><mi>foo</mi><mi>bar</mi><p>baz</table><p>quux
#errors
Line: 1 Col: 50 Unexpected start tag token (math) in the select phase. Ignored.
Line: 1 Col: 54 Unexpected start tag token (mi) in the select phase. Ignored.
Line: 1 Col: 62 Unexpected end tag (mi) in the select phase. Ignored.
Line: 1 Col: 66 Unexpected start tag token (mi) in the select phase. Ignored.
Line: 1 Col: 74 Unexpected end tag (mi) in the select phase. Ignored.
Line: 1 Col: 77 Unexpected start tag token (p) in the select phase. Ignored.
Line: 1 Col: 88 Unexpected table element end tag (tables) in the select in table phase.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <table>
| <tbody>
| <tr>
| <td>
| <select>
| "foobarbaz"
| <p>
| "quux"
#data
<!DOCTYPE html><body><table><select><math><mi>foo</mi><mi>bar</mi><p>baz</table><p>quux
#errors
Line: 1 Col: 36 Unexpected start tag (select) in table context caused voodoo mode.
Line: 1 Col: 42 Unexpected start tag token (math) in the select phase. Ignored.
Line: 1 Col: 46 Unexpected start tag token (mi) in the select phase. Ignored.
Line: 1 Col: 54 Unexpected end tag (mi) in the select phase. Ignored.
Line: 1 Col: 58 Unexpected start tag token (mi) in the select phase. Ignored.
Line: 1 Col: 66 Unexpected end tag (mi) in the select phase. Ignored.
Line: 1 Col: 69 Unexpected start tag token (p) in the select phase. Ignored.
Line: 1 Col: 80 Unexpected table element end tag (tables) in the select in table phase.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <select>
| "foobarbaz"
| <table>
| <p>
| "quux"
#data
<!DOCTYPE html><body></body></html><math><mi>foo</mi><mi>bar</mi><p>baz
#errors
Line: 1 Col: 41 Unexpected start tag (math).
Line: 1 Col: 68 HTML start tag "p" in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><body></body><math><mi>foo</mi><mi>bar</mi><p>baz
#errors
Line: 1 Col: 34 Unexpected start tag token (math) in the after body phase.
Line: 1 Col: 61 HTML start tag "p" in a foreign namespace context.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| <math math>
| <math mi>
| "foo"
| <math mi>
| "bar"
| <p>
| "baz"
#data
<!DOCTYPE html><frameset><math><mi></mi><mi></mi><p><span>
#errors
Line: 1 Col: 31 Unexpected start tag token (math) in the frameset phase. Ignored.
Line: 1 Col: 35 Unexpected start tag token (mi) in the frameset phase. Ignored.
Line: 1 Col: 40 Unexpected end tag token (mi) in the frameset phase. Ignored.
Line: 1 Col: 44 Unexpected start tag token (mi) in the frameset phase. Ignored.
Line: 1 Col: 49 Unexpected end tag token (mi) in the frameset phase. Ignored.
Line: 1 Col: 52 Unexpected start tag token (p) in the frameset phase. Ignored.
Line: 1 Col: 58 Unexpected start tag token (span) in the frameset phase. Ignored.
Line: 1 Col: 58 Expected closing tag. Unexpected end of file.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><frameset></frameset><math><mi></mi><mi></mi><p><span>
#errors
Line: 1 Col: 42 Unexpected start tag (math) in the after frameset phase. Ignored.
Line: 1 Col: 46 Unexpected start tag (mi) in the after frameset phase. Ignored.
Line: 1 Col: 51 Unexpected end tag (mi) in the after frameset phase. Ignored.
Line: 1 Col: 55 Unexpected start tag (mi) in the after frameset phase. Ignored.
Line: 1 Col: 60 Unexpected end tag (mi) in the after frameset phase. Ignored.
Line: 1 Col: 63 Unexpected start tag (p) in the after frameset phase. Ignored.
Line: 1 Col: 69 Unexpected start tag (span) in the after frameset phase. Ignored.
#document
| <!DOCTYPE html>
| <html>
| <head>
| <frameset>
#data
<!DOCTYPE html><body xlink:href=foo><math xlink:href=foo></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| <math math>
| xlink href="foo"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><math><mi xml:lang=en xlink:href=foo></mi></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <math math>
| <math mi>
| xlink href="foo"
| xml lang="en"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><math><mi xml:lang=en xlink:href=foo /></math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <math math>
| <math mi>
| xlink href="foo"
| xml lang="en"
#data
<!DOCTYPE html><body xlink:href=foo xml:lang=en><math><mi xml:lang=en xlink:href=foo />bar</math>
#errors
#document
| <!DOCTYPE html>
| <html>
| <head>
| <body>
| xlink:href="foo"
| xml:lang="en"
| <math math>
| <math mi>
| xlink href="foo"
| xml lang="en"
| "bar"

View File

@ -0,0 +1,741 @@
#data
<body><span>
#errors
#document-fragment
body
#document
| <span>
#data
<span><body>
#errors
#document-fragment
body
#document
| <span>
#data
<span><body>
#errors
#document-fragment
div
#document
| <span>
#data
<body><span>
#errors
#document-fragment
html
#document
| <head>
| <body>
| <span>
#data
<frameset><span>
#errors
#document-fragment
body
#document
| <span>
#data
<span><frameset>
#errors
#document-fragment
body
#document
| <span>
#data
<span><frameset>
#errors
#document-fragment
div
#document
| <span>
#data
<frameset><span>
#errors
#document-fragment
html
#document
| <head>
| <frameset>
#data
<table><tr>
#errors
#document-fragment
table
#document
| <tbody>
| <tr>
#data
</table><tr>
#errors
#document-fragment
table
#document
| <tbody>
| <tr>
#data
<a>
#errors
#document-fragment
table
#document
| <a>
#data
<a>
#errors
#document-fragment
table
#document
| <a>
#data
<a><caption>a
#errors
#document-fragment
table
#document
| <a>
| <caption>
| "a"
#data
<a><colgroup><col>
#errors
#document-fragment
table
#document
| <a>
| <colgroup>
| <col>
#data
<a><tbody><tr>
#errors
#document-fragment
table
#document
| <a>
| <tbody>
| <tr>
#data
<a><tfoot><tr>
#errors
#document-fragment
table
#document
| <a>
| <tfoot>
| <tr>
#data
<a><thead><tr>
#errors
#document-fragment
table
#document
| <a>
| <thead>
| <tr>
#data
<a><tr>
#errors
#document-fragment
table
#document
| <a>
| <tbody>
| <tr>
#data
<a><th>
#errors
#document-fragment
table
#document
| <a>
| <tbody>
| <tr>
| <th>
#data
<a><td>
#errors
#document-fragment
table
#document
| <a>
| <tbody>
| <tr>
| <td>
#data
<table></table><tbody>
#errors
#document-fragment
caption
#document
| <table>
#data
</table><span>
#errors
#document-fragment
caption
#document
| <span>
#data
<span></table>
#errors
#document-fragment
caption
#document
| <span>
#data
</caption><span>
#errors
#document-fragment
caption
#document
| <span>
#data
<span></caption><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><caption><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><col><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><colgroup><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><html><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><tbody><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><td><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><tfoot><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><thead><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><th><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span><tr><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
<span></table><span>
#errors
#document-fragment
caption
#document
| <span>
| <span>
#data
</colgroup><col>
#errors
#document-fragment
colgroup
#document
| <col>
#data
<a><col>
#errors
#document-fragment
colgroup
#document
| <col>
#data
<caption><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<col><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<colgroup><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<tbody><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<tfoot><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<thead><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
</table><a>
#errors
#document-fragment
tbody
#document
| <a>
#data
<a><tr>
#errors
#document-fragment
tbody
#document
| <a>
| <tr>
#data
<a><td>
#errors
#document-fragment
tbody
#document
| <a>
| <tr>
| <td>
#data
<a><td>
#errors
#document-fragment
tbody
#document
| <a>
| <tr>
| <td>
#data
<a><td>
#errors
#document-fragment
tbody
#document
| <a>
| <tr>
| <td>
#data
<td><table><tbody><a><tr>
#errors
#document-fragment
tbody
#document
| <tr>
| <td>
| <a>
| <table>
| <tbody>
| <tr>
#data
</tr><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<td><table><a><tr></tr><tr>
#errors
#document-fragment
tr
#document
| <td>
| <a>
| <table>
| <tbody>
| <tr>
| <tr>
#data
<caption><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<col><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<colgroup><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<tbody><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<tfoot><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<thead><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<tr><td>
#errors
#document-fragment
tr
#document
| <td>
#data
</table><td>
#errors
#document-fragment
tr
#document
| <td>
#data
<td><table></table><td>
#errors
#document-fragment
tr
#document
| <td>
| <table>
| <td>
#data
<td><table></table><td>
#errors
#document-fragment
tr
#document
| <td>
| <table>
| <td>
#data
<caption><a>
#errors
#document-fragment
td
#document
| <a>
#data
<col><a>
#errors
#document-fragment
td
#document
| <a>
#data
<colgroup><a>
#errors
#document-fragment
td
#document
| <a>
#data
<tbody><a>
#errors
#document-fragment
td
#document
| <a>
#data
<tfoot><a>
#errors
#document-fragment
td
#document
| <a>
#data
<th><a>
#errors
#document-fragment
td
#document
| <a>
#data
<thead><a>
#errors
#document-fragment
td
#document
| <a>
#data
<tr><a>
#errors
#document-fragment
td
#document
| <a>
#data
</table><a>
#errors
#document-fragment
td
#document
| <a>
#data
</tbody><a>
#errors
#document-fragment
td
#document
| <a>
#data
</td><a>
#errors
#document-fragment
td
#document
| <a>
#data
</tfoot><a>
#errors
#document-fragment
td
#document
| <a>
#data
</thead><a>
#errors
#document-fragment
td
#document
| <a>
#data
</th><a>
#errors
#document-fragment
td
#document
| <a>
#data
</tr><a>
#errors
#document-fragment
td
#document
| <a>
#data
<table><td><td>
#errors
#document-fragment
td
#document
| <table>
| <tbody>
| <tr>
| <td>
| <td>
#data
</select><option>
#errors
#document-fragment
select
#document
| <option>
#data
<input><option>
#errors
#document-fragment
select
#document
| <option>
#data
<keygen><option>
#errors
#document-fragment
select
#document
| <option>
#data
<textarea><option>
#errors
#document-fragment
select
#document
| <option>
#data
</html><!--abc-->
#errors
#document-fragment
html
#document
| <head>
| <body>
| <!-- abc -->
#data
</frameset><frame>
#errors
#document-fragment
frameset
#document
| <frame>
#data
#errors
#document-fragment
html
#document
| <head>
| <body>

View File

@ -0,0 +1,261 @@
#data
<b><p>Bold </b> Not bold</p>
Also not bold.
#errors
#document
| <html>
| <head>
| <body>
| <b>
| <p>
| <b>
| "Bold "
| " Not bold"
| "
Also not bold."
#data
<html>
<font color=red><i>Italic and Red<p>Italic and Red </font> Just italic.</p> Italic only.</i> Plain
<p>I should not be red. <font color=red>Red. <i>Italic and red.</p>
<p>Italic and red. </i> Red.</font> I should not be red.</p>
<b>Bold <i>Bold and italic</b> Only Italic </i> Plain
#errors
#document
| <html>
| <head>
| <body>
| <font>
| color="red"
| <i>
| "Italic and Red"
| <i>
| <p>
| <font>
| color="red"
| "Italic and Red "
| " Just italic."
| " Italic only."
| " Plain
"
| <p>
| "I should not be red. "
| <font>
| color="red"
| "Red. "
| <i>
| "Italic and red."
| <font>
| color="red"
| <i>
| "
"
| <p>
| <font>
| color="red"
| <i>
| "Italic and red. "
| " Red."
| " I should not be red."
| "
"
| <b>
| "Bold "
| <i>
| "Bold and italic"
| <i>
| " Only Italic "
| " Plain"
#data
<html><body>
<p><font size="7">First paragraph.</p>
<p>Second paragraph.</p></font>
<b><p><i>Bold and Italic</b> Italic</p>
#errors
#document
| <html>
| <head>
| <body>
| "
"
| <p>
| <font>
| size="7"
| "First paragraph."
| <font>
| size="7"
| "
"
| <p>
| "Second paragraph."
| "
"
| <b>
| <p>
| <b>
| <i>
| "Bold and Italic"
| <i>
| " Italic"
#data
<html>
<dl>
<dt><b>Boo
<dd>Goo?
</dl>
</html>
#errors
#document
| <html>
| <head>
| <body>
| <dl>
| "
"
| <dt>
| <b>
| "Boo
"
| <dd>
| <b>
| "Goo?
"
| <b>
| "
"
#data
<html><body>
<label><a><div>Hello<div>World</div></a></label>
</body></html>
#errors
#document
| <html>
| <head>
| <body>
| "
"
| <label>
| <a>
| <div>
| <a>
| "Hello"
| <div>
| "World"
| "
"
#data
<table><center> <font>a</center> <img> <tr><td> </td> </tr> </table>
#errors
#document
| <html>
| <head>
| <body>
| <center>
| " "
| <font>
| "a"
| <font>
| <img>
| " "
| <table>
| " "
| <tbody>
| <tr>
| <td>
| " "
| " "
| " "
#data
<table><tr><p><a><p>You should see this text.
#errors
#document
| <html>
| <head>
| <body>
| <p>
| <a>
| <p>
| <a>
| "You should see this text."
| <table>
| <tbody>
| <tr>
#data
<TABLE>
<TR>
<CENTER><CENTER><TD></TD></TR><TR>
<FONT>
<TABLE><tr></tr></TABLE>
</P>
<a></font><font></a>
This page contains an insanely badly-nested tag sequence.
#errors
#document
| <html>
| <head>
| <body>
| <center>
| <center>
| <font>
| "
"
| <table>
| "
"
| <tbody>
| <tr>
| "
"
| <td>
| <tr>
| "
"
| <table>
| <tbody>
| <tr>
| <font>
| "
"
| <p>
| "
"
| <a>
| <a>
| <font>
| <font>
| "
This page contains an insanely badly-nested tag sequence."
#data
<html>
<body>
<b><nobr><div>This text is in a div inside a nobr</nobr>More text that should not be in the nobr, i.e., the
nobr should have closed the div inside it implicitly. </b><pre>A pre tag outside everything else.</pre>
</body>
</html>
#errors
#document
| <html>
| <head>
| <body>
| "
"
| <b>
| <nobr>
| <div>
| <b>
| <nobr>
| "This text is in a div inside a nobr"
| "More text that should not be in the nobr, i.e., the
nobr should have closed the div inside it implicitly. "
| <pre>
| "A pre tag outside everything else."
| "
"

Some files were not shown because too many files have changed in this diff Show More